Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5283 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.9386. Min Act: -0.1700
Data Index: 2406367 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.7823. Min Act: -0.1700
Data Index: 8415797 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5636. Min Act: -0.1700
Data Index: 1007488 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5323. Min Act: -0.1700
Data Index: 4831635 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5323. Min Act: -0.1700
Data Index: 5493869 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.5323. Min Act: -0.1700
Data Index: 577901 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.4386. Min Act: -0.1700
Data Index: 3020168 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3761. Min Act: -0.1700
Data Index: 6912808 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.4073. Min Act: -0.1700
Data Index: 6994651 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3761. Min Act: -0.1700
Data Index: 1677257 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3761. Min Act: -0.1700
Data Index: 8703427 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3761. Min Act: -0.1700
Data Index: 5360924 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3448. Min Act: -0.1700
Data Index: 8406205 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3761. Min Act: -0.1700
Data Index: 6043180 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3448. Min Act: -0.1700
Data Index: 1757884 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3448. Min Act: -0.1700
Data Index: 7884039 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3136. Min Act: -0.1700
Data Index: 178297 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.2823. Min Act: -0.1700
Data Index: 1736331 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.3136. Min Act: -0.1700
Data Index: 3823196 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9386. Min Range: -5.9386
Max Act: 5.2511. Min Act: -0.1700
Data Index: 1332712 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19