Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.4005. Min Act: -0.1700
Data Index: 3175458 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.3380. Min Act: -0.1700
Data Index: 8093465 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.3380. Min Act: -0.1700
Data Index: 6078642 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.2755. Min Act: -0.1700
Data Index: 7604480 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.2130. Min Act: -0.1700
Data Index: 6907409 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.1817. Min Act: -0.1700
Data Index: 4931593 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.1817. Min Act: -0.1700
Data Index: 4549139 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.1817. Min Act: -0.1700
Data Index: 4110929 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.1817. Min Act: -0.1700
Data Index: 7294003 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.1192. Min Act: -0.1700
Data Index: 2970843 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.1192. Min Act: -0.1700
Data Index: 7409793 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.1192. Min Act: -0.1700
Data Index: 8522503 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.1192. Min Act: -0.1700
Data Index: 2421273 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.0880. Min Act: -0.1700
Data Index: 1690861 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.0255. Min Act: -0.1700
Data Index: 7103043 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.0255. Min Act: -0.1700
Data Index: 8365347 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4005. Min Range: -6.4005
Max Act: 6.0567. Min Act: -0.1700
Data Index: 4141561 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4005. Min Range: -6.4005
Max Act: 5.9942. Min Act: -0.1700
Data Index: 6486955 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4005. Min Range: -6.4005
Max Act: 5.9317. Min Act: -0.1700
Data Index: 7686530 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4005. Min Range: -6.4005
Max Act: 5.9317. Min Act: -0.1700
Data Index: 5390268 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19