Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3733 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.9377. Min Act: -0.1700
Data Index: 7517348 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.8439. Min Act: -0.1700
Data Index: 3012566 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.8126. Min Act: -0.1700
Data Index: 3936232 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.7813. Min Act: -0.1700
Data Index: 3936237 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.7500. Min Act: -0.1700
Data Index: 965474 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.7188. Min Act: -0.1700
Data Index: 490739 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.7500. Min Act: -0.1700
Data Index: 6166593 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.7031. Min Act: -0.1700
Data Index: 2046854 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.7188. Min Act: -0.1700
Data Index: 109806 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.7188. Min Act: -0.1700
Data Index: 2004353 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.7031. Min Act: -0.1700
Data Index: 400231 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.6718. Min Act: -0.1700
Data Index: 2767360 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.6875. Min Act: -0.1700
Data Index: 3936236 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.6562. Min Act: -0.1700
Data Index: 6466805 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.6718. Min Act: -0.1700
Data Index: 7191064 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.6562. Min Act: -0.1700
Data Index: 7802357 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.6405. Min Act: -0.1700
Data Index: 4331604 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.6562. Min Act: -0.1700
Data Index: 7407690 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.6405. Min Act: -0.1700
Data Index: 7546295 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9377. Min Range: -3.9377
Max Act: 3.6405. Min Act: -0.1700
Data Index: 5757391 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19