Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.8504. Min Act: -0.1700
Data Index: 4549376 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.7879. Min Act: -0.1700
Data Index: 4874568 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.7254. Min Act: -0.1700
Data Index: 2550056 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.6941. Min Act: -0.1700
Data Index: 5076978 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.6629. Min Act: -0.1700
Data Index: 1067040 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.6941. Min Act: -0.1700
Data Index: 1498689 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.6004. Min Act: -0.1700
Data Index: 6061217 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5691. Min Act: -0.1700
Data Index: 3442492 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5691. Min Act: -0.1700
Data Index: 7480772 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5379. Min Act: -0.1700
Data Index: 7766613 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5691. Min Act: -0.1700
Data Index: 3434990 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5379. Min Act: -0.1700
Data Index: 2457717 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5379. Min Act: -0.1700
Data Index: 2130684 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5066. Min Act: -0.1700
Data Index: 1671174 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5066. Min Act: -0.1700
Data Index: 86160 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5066. Min Act: -0.1700
Data Index: 2657375 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5066. Min Act: -0.1700
Data Index: 7746847 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.5066. Min Act: -0.1700
Data Index: 2184811 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.4754. Min Act: -0.1700
Data Index: 3825295 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8504. Min Range: -4.8504
Max Act: 4.4441. Min Act: -0.1700
Data Index: 4532847 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19