Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0335. Min Range: -4.0335
Max Act: 4.0335. Min Act: -0.1700
Data Index: 3155832 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.9867. Min Act: -0.1700
Data Index: 4537536 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.9398. Min Act: -0.1700
Data Index: 3418260 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.9241. Min Act: -0.1700
Data Index: 218688 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8929. Min Act: -0.1700
Data Index: 8798843 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.9085. Min Act: -0.1700
Data Index: 5374827 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8616. Min Act: -0.1700
Data Index: 2816238 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8460. Min Act: -0.1700
Data Index: 6954807 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8303. Min Act: -0.1700
Data Index: 1738789 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8460. Min Act: -0.1700
Data Index: 4908566 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8616. Min Act: -0.1700
Data Index: 1535351 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8616. Min Act: -0.1700
Data Index: 8488258 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8460. Min Act: -0.1700
Data Index: 329925 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8303. Min Act: -0.1700
Data Index: 2020773 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8303. Min Act: -0.1700
Data Index: 1353700 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8460. Min Act: -0.1700
Data Index: 3709021 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8460. Min Act: -0.1700
Data Index: 3472689 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8303. Min Act: -0.1700
Data Index: 4746847 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8460. Min Act: -0.1700
Data Index: 3930064 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0335. Min Range: -4.0335
Max Act: 3.8303. Min Act: -0.1700
Data Index: 783050 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19