Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.9481. Min Act: -0.1700
Data Index: 7976586 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 352509 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8230. Min Act: -0.1700
Data Index: 4175199 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 1721580 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8230. Min Act: -0.1700
Data Index: 2115513 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7917. Min Act: -0.1700
Data Index: 3608981 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7917. Min Act: -0.1700
Data Index: 6764503 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7917. Min Act: -0.1700
Data Index: 2999563 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7605. Min Act: -0.1700
Data Index: 2727445 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7917. Min Act: -0.1700
Data Index: 1348489 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7605. Min Act: -0.1700
Data Index: 1822518 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7448. Min Act: -0.1700
Data Index: 239815 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7605. Min Act: -0.1700
Data Index: 7557550 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7605. Min Act: -0.1700
Data Index: 6554953 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7448. Min Act: -0.1700
Data Index: 4091273 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7292. Min Act: -0.1700
Data Index: 2497798 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7448. Min Act: -0.1700
Data Index: 2866029 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7605. Min Act: -0.1700
Data Index: 2203046 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7135. Min Act: -0.1700
Data Index: 4689012 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.7135. Min Act: -0.1700
Data Index: 1561385 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19