Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.3212. Min Act: -0.1700
Data Index: 7792320 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.2587. Min Act: -0.1700
Data Index: 8365600 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.2587. Min Act: -0.1700
Data Index: 3582980 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.1962. Min Act: -0.1700
Data Index: 8345421 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.1649. Min Act: -0.1700
Data Index: 6195586 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.1337. Min Act: -0.1700
Data Index: 4392900 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.1337. Min Act: -0.1700
Data Index: 1113864 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.1337. Min Act: -0.1700
Data Index: 2592434 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.1024. Min Act: -0.1700
Data Index: 3716630 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.1024. Min Act: -0.1700
Data Index: 47098 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0712. Min Act: -0.1700
Data Index: 536419 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0712. Min Act: -0.1700
Data Index: 5799971 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0712. Min Act: -0.1700
Data Index: 7190683 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0712. Min Act: -0.1700
Data Index: 1278470 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0399. Min Act: -0.1700
Data Index: 1518727 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0399. Min Act: -0.1700
Data Index: 1404180 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0712. Min Act: -0.1700
Data Index: 7414089 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0712. Min Act: -0.1700
Data Index: 7182107 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0399. Min Act: -0.1700
Data Index: 594308 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3212. Min Range: -4.3212
Max Act: 4.0399. Min Act: -0.1700
Data Index: 3435279 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19