Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2393 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0366. Min Range: -6.0366
Max Act: 6.0366. Min Act: -0.1700
Data Index: 7837282 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0366. Min Range: -6.0366
Max Act: 6.0053. Min Act: -0.1700
Data Index: 2216052 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.9428. Min Act: -0.1700
Data Index: 863599 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.9428. Min Act: -0.1700
Data Index: 3350256 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.9741. Min Act: -0.1700
Data Index: 5674475 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.9428. Min Act: -0.1700
Data Index: 3126768 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.8803. Min Act: -0.1700
Data Index: 899916 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.8803. Min Act: -0.1700
Data Index: 8632558 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.8491. Min Act: -0.1700
Data Index: 5858878 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.8178. Min Act: -0.1700
Data Index: 4652653 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7866. Min Act: -0.1700
Data Index: 1944244 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7866. Min Act: -0.1700
Data Index: 4908492 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7866. Min Act: -0.1700
Data Index: 5415316 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7866. Min Act: -0.1700
Data Index: 3430363 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7553. Min Act: -0.1700
Data Index: 6835087 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7553. Min Act: -0.1700
Data Index: 966763 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7241. Min Act: -0.1700
Data Index: 2270480 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7241. Min Act: -0.1700
Data Index: 5287585 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7241. Min Act: -0.1700
Data Index: 2307041 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0366. Min Range: -6.0366
Max Act: 5.7241. Min Act: -0.1700
Data Index: 5379195 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19