Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5514 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.5209. Min Act: -0.1700
Data Index: 2881435 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.1146. Min Act: -0.1700
Data Index: 5209739 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0834. Min Act: -0.1700
Data Index: 6223106 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0521. Min Act: -0.1700
Data Index: 4432854 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0521. Min Act: -0.1700
Data Index: 6016024 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0209. Min Act: -0.1700
Data Index: 6947574 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0209. Min Act: -0.1700
Data Index: 422151 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0209. Min Act: -0.1700
Data Index: 6482962 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.9896. Min Act: -0.1700
Data Index: 3955669 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.9584. Min Act: -0.1700
Data Index: 3577757 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8959. Min Act: -0.1700
Data Index: 6763914 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8646. Min Act: -0.1700
Data Index: 7139951 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8646. Min Act: -0.1700
Data Index: 5000939 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8334. Min Act: -0.1700
Data Index: 330227 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8646. Min Act: -0.1700
Data Index: 4793459 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8646. Min Act: -0.1700
Data Index: 3199557 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8646. Min Act: -0.1700
Data Index: 6223107 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8334. Min Act: -0.1700
Data Index: 4821519 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8646. Min Act: -0.1700
Data Index: 5981679 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.8334. Min Act: -0.1700
Data Index: 3183124 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19