Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.9351. Min Act: -0.1700
Data Index: 5340264 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.8101. Min Act: -0.1700
Data Index: 1499 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.7789. Min Act: -0.1700
Data Index: 6832382 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.6539. Min Act: -0.1700
Data Index: 89093 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.6539. Min Act: -0.1700
Data Index: 8322184 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.6226. Min Act: -0.1700
Data Index: 750188 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.5914. Min Act: -0.1700
Data Index: 4243012 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.5289. Min Act: -0.1700
Data Index: 4044431 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.5289. Min Act: -0.1700
Data Index: 8809398 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.4976. Min Act: -0.1700
Data Index: 3265453 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.4664. Min Act: -0.1700
Data Index: 3078769 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.4351. Min Act: -0.1700
Data Index: 8798452 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.4039. Min Act: -0.1700
Data Index: 504524 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.4039. Min Act: -0.1700
Data Index: 1295381 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.4039. Min Act: -0.1700
Data Index: 1766297 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.3726. Min Act: -0.1700
Data Index: 769577 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.3726. Min Act: -0.1700
Data Index: 683650 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.3726. Min Act: -0.1700
Data Index: 3916948 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.3414. Min Act: -0.1700
Data Index: 1326136 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9351. Min Range: -5.9351
Max Act: 5.3414. Min Act: -0.1700
Data Index: 2876175 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19