Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4000 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.3182. Min Act: -0.1700
Data Index: 6450609 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.1932. Min Act: -0.1700
Data Index: 1003844 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.2244. Min Act: -0.1700
Data Index: 2197407 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.1932. Min Act: -0.1700
Data Index: 133114 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0994. Min Act: -0.1700
Data Index: 8658138 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.1307. Min Act: -0.1700
Data Index: 530035 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.1307. Min Act: -0.1700
Data Index: 7336304 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0682. Min Act: -0.1700
Data Index: 2924282 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0369. Min Act: -0.1700
Data Index: 1572062 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0682. Min Act: -0.1700
Data Index: 5095814 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0369. Min Act: -0.1700
Data Index: 5216119 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0369. Min Act: -0.1700
Data Index: 4298834 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0057. Min Act: -0.1700
Data Index: 61874 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0057. Min Act: -0.1700
Data Index: 95145 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0057. Min Act: -0.1700
Data Index: 4919604 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3182. Min Range: -5.3182
Max Act: 5.0057. Min Act: -0.1700
Data Index: 2640933 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3182. Min Range: -5.3182
Max Act: 4.9432. Min Act: -0.1700
Data Index: 882748 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3182. Min Range: -5.3182
Max Act: 4.9744. Min Act: -0.1700
Data Index: 3757708 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3182. Min Range: -5.3182
Max Act: 4.9432. Min Act: -0.1700
Data Index: 2689645 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3182. Min Range: -5.3182
Max Act: 4.9744. Min Act: -0.1700
Data Index: 595007 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19