Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3917 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2740. Min Range: -7.2740
Max Act: 7.2740. Min Act: -0.1700
Data Index: 5093880 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2740. Min Range: -7.2740
Max Act: 7.2740. Min Act: -0.1700
Data Index: 3580575 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.9302. Min Act: -0.1700
Data Index: 2035990 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.8990. Min Act: -0.1700
Data Index: 5310790 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.8990. Min Act: -0.1700
Data Index: 4466193 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.8990. Min Act: -0.1700
Data Index: 5315249 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.8677. Min Act: -0.1700
Data Index: 8099089 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.8365. Min Act: -0.1700
Data Index: 8553860 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.7740. Min Act: -0.1700
Data Index: 3221878 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.8052. Min Act: -0.1700
Data Index: 7662831 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.8052. Min Act: -0.1700
Data Index: 33287 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.7740. Min Act: -0.1700
Data Index: 2224395 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.7427. Min Act: -0.1700
Data Index: 1591862 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.7427. Min Act: -0.1700
Data Index: 5713054 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.7427. Min Act: -0.1700
Data Index: 5781709 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.7427. Min Act: -0.1700
Data Index: 1107533 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.7115. Min Act: -0.1700
Data Index: 3186098 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.6490. Min Act: -0.1700
Data Index: 7240215 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.6802. Min Act: -0.1700
Data Index: 4784213 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2740. Min Range: -7.2740
Max Act: 6.6490. Min Act: -0.1700
Data Index: 2362935 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19