Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2120 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1174. Min Range: -6.1174
Max Act: 6.1174. Min Act: -0.1700
Data Index: 3322745 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1174. Min Range: -6.1174
Max Act: 6.0861. Min Act: -0.1700
Data Index: 3084894 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1174. Min Range: -6.1174
Max Act: 6.0861. Min Act: -0.1700
Data Index: 8775090 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1174. Min Range: -6.1174
Max Act: 6.0549. Min Act: -0.1700
Data Index: 8414065 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.9924. Min Act: -0.1700
Data Index: 5038276 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1174. Min Range: -6.1174
Max Act: 6.0236. Min Act: -0.1700
Data Index: 5670412 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.9611. Min Act: -0.1700
Data Index: 271040 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.9611. Min Act: -0.1700
Data Index: 6386559 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.9611. Min Act: -0.1700
Data Index: 8630893 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.9611. Min Act: -0.1700
Data Index: 6610475 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.9611. Min Act: -0.1700
Data Index: 808627 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.9299. Min Act: -0.1700
Data Index: 6140440 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.9299. Min Act: -0.1700
Data Index: 3173863 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.8986. Min Act: -0.1700
Data Index: 4047957 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.8986. Min Act: -0.1700
Data Index: 7530044 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.8986. Min Act: -0.1700
Data Index: 7323499 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.8986. Min Act: -0.1700
Data Index: 3084895 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.8674. Min Act: -0.1700
Data Index: 2466194 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.8674. Min Act: -0.1700
Data Index: 782069 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1174. Min Range: -6.1174
Max Act: 5.8986. Min Act: -0.1700
Data Index: 288857 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19