Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6250 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.9292. Min Act: -0.1700
Data Index: 1355298 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.8042. Min Act: -0.1700
Data Index: 861831 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.7730. Min Act: -0.1700
Data Index: 306836 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.7730. Min Act: -0.1700
Data Index: 260395 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.7105. Min Act: -0.1700
Data Index: 3614363 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.7105. Min Act: -0.1700
Data Index: 897098 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.7105. Min Act: -0.1700
Data Index: 7638726 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.7105. Min Act: -0.1700
Data Index: 7088710 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.6792. Min Act: -0.1700
Data Index: 5556833 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.6480. Min Act: -0.1700
Data Index: 1792201 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.6480. Min Act: -0.1700
Data Index: 8117406 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.6792. Min Act: -0.1700
Data Index: 2919380 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.6480. Min Act: -0.1700
Data Index: 4410711 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.6167. Min Act: -0.1700
Data Index: 1499394 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.6167. Min Act: -0.1700
Data Index: 3132703 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.5855. Min Act: -0.1700
Data Index: 2720797 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.5855. Min Act: -0.1700
Data Index: 5604674 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.5855. Min Act: -0.1700
Data Index: 6494829 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.5855. Min Act: -0.1700
Data Index: 7818283 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9292. Min Range: -4.9292
Max Act: 4.5855. Min Act: -0.1700
Data Index: 1321239 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19