Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1621 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0802. Min Range: -6.0802
Max Act: 6.0802. Min Act: -0.1700
Data Index: 3013641 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0802. Min Range: -6.0802
Max Act: 6.0490. Min Act: -0.1700
Data Index: 6743805 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0802. Min Range: -6.0802
Max Act: 6.0177. Min Act: -0.1700
Data Index: 7602404 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0802. Min Range: -6.0802
Max Act: 6.0177. Min Act: -0.1700
Data Index: 3336395 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9865. Min Act: -0.1700
Data Index: 6962634 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9865. Min Act: -0.1700
Data Index: 2193905 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9552. Min Act: -0.1700
Data Index: 376905 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9552. Min Act: -0.1700
Data Index: 1925274 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9240. Min Act: -0.1700
Data Index: 3786799 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9240. Min Act: -0.1700
Data Index: 892547 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.8927. Min Act: -0.1700
Data Index: 2807330 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9240. Min Act: -0.1700
Data Index: 4244089 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9240. Min Act: -0.1700
Data Index: 6251252 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.8927. Min Act: -0.1700
Data Index: 3197452 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9240. Min Act: -0.1700
Data Index: 2967112 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.9240. Min Act: -0.1700
Data Index: 2529131 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.8927. Min Act: -0.1700
Data Index: 5685128 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.8927. Min Act: -0.1700
Data Index: 3455533 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.8927. Min Act: -0.1700
Data Index: 1582124 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0802. Min Range: -6.0802
Max Act: 5.8927. Min Act: -0.1700
Data Index: 5254011 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19