Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.6163. Min Act: -0.1700
Data Index: 5752678 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.7444. Min Act: -0.1700
Data Index: 3164347 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.5680. Min Act: -0.1700
Data Index: 8231611 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.5680. Min Act: -0.1700
Data Index: 6361324 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.5841. Min Act: -0.1700
Data Index: 7244578 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.5680. Min Act: -0.1700
Data Index: 6068836 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.5357. Min Act: -0.1700
Data Index: 1463836 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.5195. Min Act: -0.1700
Data Index: 2152360 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.5033. Min Act: -0.1700
Data Index: 794788 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.5518. Min Act: -0.1700
Data Index: 7262239 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4871. Min Act: -0.1700
Data Index: 7479583 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4871. Min Act: -0.1700
Data Index: 4281829 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4384. Min Act: -0.1700
Data Index: 1382278 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4221. Min Act: -0.1700
Data Index: 7185226 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4058. Min Act: -0.1700
Data Index: 2517332 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4221. Min Act: -0.1700
Data Index: 4441325 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4709. Min Act: -0.1700
Data Index: 7899479 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4871. Min Act: -0.1700
Data Index: 220595 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4384. Min Act: -0.1700
Data Index: 7629804 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7444. Min Range: -2.7444
Max Act: 2.4871. Min Act: -0.1700
Data Index: 1027615 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19