Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2832 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.8374. Min Act: -0.1700
Data Index: 8188673 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.5562. Min Act: -0.1700
Data Index: 548327 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.5249. Min Act: -0.1700
Data Index: 6200954 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.5249. Min Act: -0.1700
Data Index: 6092054 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.5249. Min Act: -0.1700
Data Index: 769873 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.4937. Min Act: -0.1700
Data Index: 8423329 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.4937. Min Act: -0.1700
Data Index: 727298 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.4937. Min Act: -0.1700
Data Index: 391949 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.4937. Min Act: -0.1700
Data Index: 4873556 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.4624. Min Act: -0.1700
Data Index: 2535776 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.4624. Min Act: -0.1700
Data Index: 2396773 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.4312. Min Act: -0.1700
Data Index: 1419455 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.4312. Min Act: -0.1700
Data Index: 1353958 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.4312. Min Act: -0.1700
Data Index: 1212506 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.3999. Min Act: -0.1700
Data Index: 3980525 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.3687. Min Act: -0.1700
Data Index: 7659280 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.3374. Min Act: -0.1700
Data Index: 1353959 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.3374. Min Act: -0.1700
Data Index: 2905192 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.3062. Min Act: -0.1700
Data Index: 3179645 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8374. Min Range: -5.8374
Max Act: 5.3062. Min Act: -0.1700
Data Index: 8070959 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19