Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4948 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.7381. Min Act: -0.1700
Data Index: 7412 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.6131. Min Act: -0.1700
Data Index: 2102335 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.6131. Min Act: -0.1700
Data Index: 3073636 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.6131. Min Act: -0.1700
Data Index: 473099 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.5819. Min Act: -0.1700
Data Index: 4210616 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.5819. Min Act: -0.1700
Data Index: 3958015 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.5819. Min Act: -0.1700
Data Index: 4744787 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.5506. Min Act: -0.1700
Data Index: 1664338 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.5194. Min Act: -0.1700
Data Index: 4260944 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.5194. Min Act: -0.1700
Data Index: 5306916 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.4881. Min Act: -0.1700
Data Index: 548521 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.4881. Min Act: -0.1700
Data Index: 577728 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.4256. Min Act: -0.1700
Data Index: 409416 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.3944. Min Act: -0.1700
Data Index: 2793631 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.4256. Min Act: -0.1700
Data Index: 1269155 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.4256. Min Act: -0.1700
Data Index: 2399457 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.3944. Min Act: -0.1700
Data Index: 4950190 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.3944. Min Act: -0.1700
Data Index: 4888568 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.3944. Min Act: -0.1700
Data Index: 515427 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7381. Min Range: -6.7381
Max Act: 6.3944. Min Act: -0.1700
Data Index: 5196342 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19