Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3189 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.9198. Min Act: -0.1700
Data Index: 6896464 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.8573. Min Act: -0.1700
Data Index: 3196773 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.7635. Min Act: -0.1700
Data Index: 5387775 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.7010. Min Act: -0.1700
Data Index: 5995595 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.7010. Min Act: -0.1700
Data Index: 2123389 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6698. Min Act: -0.1700
Data Index: 1680452 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6385. Min Act: -0.1700
Data Index: 494431 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6385. Min Act: -0.1700
Data Index: 1335370 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6385. Min Act: -0.1700
Data Index: 564306 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6385. Min Act: -0.1700
Data Index: 93271 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6385. Min Act: -0.1700
Data Index: 8725090 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6385. Min Act: -0.1700
Data Index: 7503712 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6385. Min Act: -0.1700
Data Index: 5556545 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6073. Min Act: -0.1700
Data Index: 4387722 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6073. Min Act: -0.1700
Data Index: 2795076 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6073. Min Act: -0.1700
Data Index: 1365485 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6385. Min Act: -0.1700
Data Index: 5015131 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6073. Min Act: -0.1700
Data Index: 7648927 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6073. Min Act: -0.1700
Data Index: 5183306 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9198. Min Range: -4.9198
Max Act: 4.6073. Min Act: -0.1700
Data Index: 3118780 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19