Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.9678. Min Act: -0.1700
Data Index: 812124 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.9365. Min Act: -0.1700
Data Index: 7252536 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.8428. Min Act: -0.1700
Data Index: 971135 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.8115. Min Act: -0.1700
Data Index: 6713773 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.8115. Min Act: -0.1700
Data Index: 3330695 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.7803. Min Act: -0.1700
Data Index: 554064 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.7490. Min Act: -0.1700
Data Index: 3473498 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.7490. Min Act: -0.1700
Data Index: 8325183 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.7490. Min Act: -0.1700
Data Index: 1692330 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.7178. Min Act: -0.1700
Data Index: 1371610 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.7178. Min Act: -0.1700
Data Index: 5801586 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6865. Min Act: -0.1700
Data Index: 3144662 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6865. Min Act: -0.1700
Data Index: 802312 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6553. Min Act: -0.1700
Data Index: 3161945 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6240. Min Act: -0.1700
Data Index: 1780385 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6240. Min Act: -0.1700
Data Index: 3505928 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6240. Min Act: -0.1700
Data Index: 4643861 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.6240. Min Act: -0.1700
Data Index: 1069980 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.5928. Min Act: -0.1700
Data Index: 6781100 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9678. Min Range: -5.9678
Max Act: 5.5928. Min Act: -0.1700
Data Index: 6787200 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19