Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3111 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0008. Min Range: -7.0008
Max Act: 7.0008. Min Act: -0.1700
Data Index: 3854747 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.9695. Min Act: -0.1700
Data Index: 758740 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.7820. Min Act: -0.1700
Data Index: 4147989 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.7508. Min Act: -0.1700
Data Index: 5620399 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.7195. Min Act: -0.1700
Data Index: 6639289 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.6883. Min Act: -0.1700
Data Index: 5223749 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.7195. Min Act: -0.1700
Data Index: 8201710 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.7195. Min Act: -0.1700
Data Index: 116555 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.6570. Min Act: -0.1700
Data Index: 6793784 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.6258. Min Act: -0.1700
Data Index: 890232 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.6258. Min Act: -0.1700
Data Index: 7114006 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.5945. Min Act: -0.1700
Data Index: 5453534 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.5320. Min Act: -0.1700
Data Index: 2500308 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.5320. Min Act: -0.1700
Data Index: 3660679 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.5320. Min Act: -0.1700
Data Index: 4316915 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.5320. Min Act: -0.1700
Data Index: 3592214 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.5008. Min Act: -0.1700
Data Index: 2874184 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.5008. Min Act: -0.1700
Data Index: 8215701 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.4695. Min Act: -0.1700
Data Index: 5285762 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0008. Min Range: -7.0008
Max Act: 6.4695. Min Act: -0.1700
Data Index: 768907 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19