Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3114 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2821. Min Act: -0.1700
Data Index: 7685944 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2821. Min Act: -0.1700
Data Index: 305830 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2821. Min Act: -0.1700
Data Index: 4050537 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2508. Min Act: -0.1700
Data Index: 8675880 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2508. Min Act: -0.1700
Data Index: 4934944 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2508. Min Act: -0.1700
Data Index: 6386957 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2508. Min Act: -0.1700
Data Index: 2197419 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2821. Min Act: -0.1700
Data Index: 6566900 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2196. Min Act: -0.1700
Data Index: 1033845 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2196. Min Act: -0.1700
Data Index: 1552119 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2196. Min Act: -0.1700
Data Index: 2301276 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.1883. Min Act: -0.1700
Data Index: 5273263 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2196. Min Act: -0.1700
Data Index: 5136823 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.2196. Min Act: -0.1700
Data Index: 7070647 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.1883. Min Act: -0.1700
Data Index: 4036952 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.1883. Min Act: -0.1700
Data Index: 5360450 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.1883. Min Act: -0.1700
Data Index: 4173558 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.1883. Min Act: -0.1700
Data Index: 5569832 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.1883. Min Act: -0.1700
Data Index: 3948178 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2821. Min Range: -5.2821
Max Act: 5.1883. Min Act: -0.1700
Data Index: 6269099 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19