Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 260 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0238. Min Range: -2.0238
Max Act: 2.0238. Min Act: -0.1700
Data Index: 1958380 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0238. Min Range: -2.0238
Max Act: 2.0153. Min Act: -0.1700
Data Index: 5179301 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8795. Min Act: -0.1700
Data Index: 85807 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8195. Min Act: -0.1700
Data Index: 5617378 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8452. Min Act: -0.1700
Data Index: 4802287 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8452. Min Act: -0.1700
Data Index: 6383783 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8624. Min Act: -0.1700
Data Index: 8297006 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8281. Min Act: -0.1700
Data Index: 101640 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8195. Min Act: -0.1700
Data Index: 7447312 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.7937. Min Act: -0.1700
Data Index: 3258584 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8109. Min Act: -0.1700
Data Index: 4311411 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8367. Min Act: -0.1700
Data Index: 7648056 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8023. Min Act: -0.1700
Data Index: 2418378 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.8195. Min Act: -0.1700
Data Index: 5846031 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.7937. Min Act: -0.1700
Data Index: 5789933 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.7851. Min Act: -0.1700
Data Index: 3671866 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.7679. Min Act: -0.1700
Data Index: 1109891 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.7765. Min Act: -0.1700
Data Index: 516646 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.7679. Min Act: -0.1700
Data Index: 3723110 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0238. Min Range: -2.0238
Max Act: 1.7592. Min Act: -0.1700
Data Index: 5114935 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19