Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1051 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1960. Min Range: -6.1960
Max Act: 6.1960. Min Act: -0.1700
Data Index: 915266 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1960. Min Range: -6.1960
Max Act: 6.1022. Min Act: -0.1700
Data Index: 6358859 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1960. Min Range: -6.1960
Max Act: 6.0397. Min Act: -0.1700
Data Index: 5163411 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.9772. Min Act: -0.1700
Data Index: 533608 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.9460. Min Act: -0.1700
Data Index: 5356781 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.9147. Min Act: -0.1700
Data Index: 702964 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.9460. Min Act: -0.1700
Data Index: 6384886 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.9147. Min Act: -0.1700
Data Index: 535194 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.9147. Min Act: -0.1700
Data Index: 4936846 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8522. Min Act: -0.1700
Data Index: 2501542 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8522. Min Act: -0.1700
Data Index: 1155742 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8835. Min Act: -0.1700
Data Index: 2587693 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8522. Min Act: -0.1700
Data Index: 261596 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8522. Min Act: -0.1700
Data Index: 4895656 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.8210. Min Act: -0.1700
Data Index: 6061577 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7897. Min Act: -0.1700
Data Index: 34773 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7897. Min Act: -0.1700
Data Index: 3674539 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7897. Min Act: -0.1700
Data Index: 1136504 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7585. Min Act: -0.1700
Data Index: 6136999 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1960. Min Range: -6.1960
Max Act: 5.7272. Min Act: -0.1700
Data Index: 5781828 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19