Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.4785. Min Act: -0.1700
Data Index: 700902 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.3535. Min Act: -0.1700
Data Index: 2682387 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.3535. Min Act: -0.1700
Data Index: 1644026 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.2910. Min Act: -0.1700
Data Index: 4053706 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.2910. Min Act: -0.1700
Data Index: 7735612 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.2598. Min Act: -0.1700
Data Index: 2052210 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.1660. Min Act: -0.1700
Data Index: 4256885 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.1973. Min Act: -0.1700
Data Index: 6149801 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.1348. Min Act: -0.1700
Data Index: 6393482 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.1035. Min Act: -0.1700
Data Index: 5344029 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.1348. Min Act: -0.1700
Data Index: 6567570 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.1348. Min Act: -0.1700
Data Index: 6700247 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.1035. Min Act: -0.1700
Data Index: 6046993 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.0723. Min Act: -0.1700
Data Index: 6332440 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.0410. Min Act: -0.1700
Data Index: 4676815 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.0723. Min Act: -0.1700
Data Index: 5351883 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.0098. Min Act: -0.1700
Data Index: 6176947 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4785. Min Range: -7.4785
Max Act: 7.0098. Min Act: -0.1700
Data Index: 8045453 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4785. Min Range: -7.4785
Max Act: 6.9785. Min Act: -0.1700
Data Index: 778895 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4785. Min Range: -7.4785
Max Act: 6.9473. Min Act: -0.1700
Data Index: 2676971 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19