Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4752 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.3272. Min Act: -0.1700
Data Index: 3720129 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.2334. Min Act: -0.1700
Data Index: 4101346 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.2022. Min Act: -0.1700
Data Index: 5254168 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1709. Min Act: -0.1700
Data Index: 8607197 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.2022. Min Act: -0.1700
Data Index: 1481864 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1397. Min Act: -0.1700
Data Index: 6776829 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1397. Min Act: -0.1700
Data Index: 4984519 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1397. Min Act: -0.1700
Data Index: 3787162 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1397. Min Act: -0.1700
Data Index: 478984 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1084. Min Act: -0.1700
Data Index: 7887881 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1084. Min Act: -0.1700
Data Index: 8108967 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1084. Min Act: -0.1700
Data Index: 5939286 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.0772. Min Act: -0.1700
Data Index: 8358870 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1084. Min Act: -0.1700
Data Index: 1683136 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1084. Min Act: -0.1700
Data Index: 926693 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.0772. Min Act: -0.1700
Data Index: 220101 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.1084. Min Act: -0.1700
Data Index: 7081012 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.0772. Min Act: -0.1700
Data Index: 573835 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.0147. Min Act: -0.1700
Data Index: 2760138 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3272. Min Range: -5.3272
Max Act: 5.0459. Min Act: -0.1700
Data Index: 5609269 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19