Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1952 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 21.5819. Min Range: -21.5819
Max Act: 21.5819. Min Act: -0.1700
Data Index: 344411 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 21.5819. Min Range: -21.5819
Max Act: 21.3319. Min Act: -0.1700
Data Index: 6508024 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 21.5819. Min Range: -21.5819
Max Act: 21.2069. Min Act: -0.1700
Data Index: 5021425 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 21.5819. Min Range: -21.5819
Max Act: 21.2069. Min Act: -0.1700
Data Index: 1374761 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.9569. Min Act: -0.1698
Data Index: 4221695 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.9569. Min Act: -0.1699
Data Index: 5294494 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.7069. Min Act: -0.1700
Data Index: 7569559 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.7069. Min Act: -0.1700
Data Index: 1006504 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.5819. Min Act: -0.1700
Data Index: 3804995 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.5819. Min Act: -0.1700
Data Index: 31778 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.5819. Min Act: -0.1700
Data Index: 8458435 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.5819. Min Act: -0.1700
Data Index: 5294493 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.5819. Min Act: -0.1692
Data Index: 7569558 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.4569. Min Act: -0.1700
Data Index: 8544768 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.4569. Min Act: -0.1699
Data Index: 5144256 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.4569. Min Act: -0.1697
Data Index: 3013204 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.4569. Min Act: -0.1700
Data Index: 571265 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.4569. Min Act: -0.1700
Data Index: 6387947 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.3319. Min Act: -0.1700
Data Index: 3013202 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 21.5819. Min Range: -21.5819
Max Act: 20.3319. Min Act: -0.1700
Data Index: 6056164 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19