Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1027 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.8327. Min Act: -0.1700
Data Index: 5696576 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.6452. Min Act: -0.1700
Data Index: 288389 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.6452. Min Act: -0.1700
Data Index: 392619 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.6139. Min Act: -0.1700
Data Index: 228895 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.6139. Min Act: -0.1700
Data Index: 5306634 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.5514. Min Act: -0.1700
Data Index: 241004 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.5202. Min Act: -0.1700
Data Index: 222285 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.5202. Min Act: -0.1700
Data Index: 3278605 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4889. Min Act: -0.1700
Data Index: 1117517 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4889. Min Act: -0.1700
Data Index: 6919568 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4264. Min Act: -0.1700
Data Index: 3719274 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4577. Min Act: -0.1700
Data Index: 871649 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4577. Min Act: -0.1700
Data Index: 3520432 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4577. Min Act: -0.1700
Data Index: 172685 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4264. Min Act: -0.1700
Data Index: 8013784 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4577. Min Act: -0.1700
Data Index: 2594236 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4264. Min Act: -0.1700
Data Index: 262038 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.3952. Min Act: -0.1700
Data Index: 7636760 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4264. Min Act: -0.1700
Data Index: 1731990 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8327. Min Range: -5.8327
Max Act: 5.4264. Min Act: -0.1700
Data Index: 6532207 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19