Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.4365. Min Act: -0.1700
Data Index: 1016746 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.4365. Min Act: -0.1700
Data Index: 1953076 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.3428. Min Act: -0.1700
Data Index: 46219 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.2178. Min Act: -0.1700
Data Index: 6700074 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.2490. Min Act: -0.1700
Data Index: 117147 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1865. Min Act: -0.1700
Data Index: 1529023 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1553. Min Act: -0.1700
Data Index: 582168 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1240. Min Act: -0.1700
Data Index: 7291896 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1553. Min Act: -0.1700
Data Index: 1963261 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1553. Min Act: -0.1700
Data Index: 2327766 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1553. Min Act: -0.1700
Data Index: 383332 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1240. Min Act: -0.1700
Data Index: 4977377 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1553. Min Act: -0.1700
Data Index: 5894254 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1240. Min Act: -0.1700
Data Index: 4802614 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.0928. Min Act: -0.1700
Data Index: 8336003 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.0928. Min Act: -0.1700
Data Index: 7429062 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.0928. Min Act: -0.1700
Data Index: 6734424 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.1553. Min Act: -0.1700
Data Index: 3282108 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.0928. Min Act: -0.1700
Data Index: 7239427 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4365. Min Range: -5.4365
Max Act: 5.0928. Min Act: -0.1700
Data Index: 6034418 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19