Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.5782. Min Act: -0.1700
Data Index: 7884673 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.4220. Min Act: -0.1700
Data Index: 5049686 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.4532. Min Act: -0.1700
Data Index: 5091505 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.4220. Min Act: -0.1700
Data Index: 5620543 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.3907. Min Act: -0.1700
Data Index: 318411 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.3282. Min Act: -0.1700
Data Index: 5684716 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.3282. Min Act: -0.1700
Data Index: 7931416 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.3282. Min Act: -0.1700
Data Index: 6488316 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.3282. Min Act: -0.1700
Data Index: 7602021 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.3282. Min Act: -0.1700
Data Index: 225259 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.2657. Min Act: -0.1700
Data Index: 4440643 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.2657. Min Act: -0.1700
Data Index: 6738328 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.1407. Min Act: -0.1700
Data Index: 4319139 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.1407. Min Act: -0.1700
Data Index: 7750975 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.0782. Min Act: -0.1700
Data Index: 6346823 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5782. Min Range: -7.5782
Max Act: 7.0157. Min Act: -0.1700
Data Index: 8264780 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5782. Min Range: -7.5782
Max Act: 6.9220. Min Act: -0.1700
Data Index: 4113010 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5782. Min Range: -7.5782
Max Act: 6.8907. Min Act: -0.1700
Data Index: 321483 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5782. Min Range: -7.5782
Max Act: 6.8282. Min Act: -0.1700
Data Index: 6174077 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5782. Min Range: -7.5782
Max Act: 6.7970. Min Act: -0.1700
Data Index: 1654963 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19