Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2859 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1375. Min Range: -5.1375
Max Act: 5.1375. Min Act: -0.1700
Data Index: 736289 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1375. Min Range: -5.1375
Max Act: 5.0438. Min Act: -0.1700
Data Index: 5316468 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.9188. Min Act: -0.1700
Data Index: 5799484 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.9188. Min Act: -0.1700
Data Index: 664450 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.8875. Min Act: -0.1700
Data Index: 5697241 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.8563. Min Act: -0.1700
Data Index: 4179408 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.8250. Min Act: -0.1700
Data Index: 1029521 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7938. Min Act: -0.1700
Data Index: 823779 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7625. Min Act: -0.1700
Data Index: 7961270 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7625. Min Act: -0.1700
Data Index: 2443993 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7313. Min Act: -0.1700
Data Index: 7291964 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7313. Min Act: -0.1700
Data Index: 5638138 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7000. Min Act: -0.1700
Data Index: 1361266 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7313. Min Act: -0.1700
Data Index: 4065818 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7313. Min Act: -0.1700
Data Index: 1398517 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7000. Min Act: -0.1700
Data Index: 6036427 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7000. Min Act: -0.1700
Data Index: 4800272 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7000. Min Act: -0.1700
Data Index: 5144055 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7000. Min Act: -0.1700
Data Index: 7976282 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1375. Min Range: -5.1375
Max Act: 4.7313. Min Act: -0.1700
Data Index: 5041594 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19