Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4724 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.5076. Min Act: -0.1700
Data Index: 5724504 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.4138. Min Act: -0.1700
Data Index: 483475 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.3826. Min Act: -0.1700
Data Index: 1603066 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.2888. Min Act: -0.1700
Data Index: 4410766 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.2576. Min Act: -0.1700
Data Index: 1575689 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.2263. Min Act: -0.1700
Data Index: 7027568 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.1326. Min Act: -0.1700
Data Index: 4199948 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.1326. Min Act: -0.1700
Data Index: 109340 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.1013. Min Act: -0.1700
Data Index: 792394 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.0701. Min Act: -0.1700
Data Index: 5598852 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.0701. Min Act: -0.1700
Data Index: 6661308 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.0388. Min Act: -0.1700
Data Index: 2703833 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.0388. Min Act: -0.1700
Data Index: 6936708 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.0076. Min Act: -0.1700
Data Index: 7293777 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.0076. Min Act: -0.1700
Data Index: 8762316 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5076. Min Range: -5.5076
Max Act: 5.0076. Min Act: -0.1700
Data Index: 4167185 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5076. Min Range: -5.5076
Max Act: 4.9763. Min Act: -0.1700
Data Index: 2180247 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5076. Min Range: -5.5076
Max Act: 4.9451. Min Act: -0.1700
Data Index: 4479904 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5076. Min Range: -5.5076
Max Act: 4.9451. Min Act: -0.1700
Data Index: 4522409 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5076. Min Range: -5.5076
Max Act: 4.9763. Min Act: -0.1700
Data Index: 6614647 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19