Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 824 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.6603. Min Act: -0.1700
Data Index: 5009113 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.6603. Min Act: -0.1700
Data Index: 2743462 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.5961. Min Act: -0.1700
Data Index: 8366317 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.6122. Min Act: -0.1700
Data Index: 3778496 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.5800. Min Act: -0.1700
Data Index: 6666137 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.5477. Min Act: -0.1700
Data Index: 1702938 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.5477. Min Act: -0.1700
Data Index: 6664850 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.5315. Min Act: -0.1700
Data Index: 4711906 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4992. Min Act: -0.1700
Data Index: 8704558 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4830. Min Act: -0.1700
Data Index: 959871 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4830. Min Act: -0.1700
Data Index: 8304638 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4667. Min Act: -0.1700
Data Index: 3573368 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4505. Min Act: -0.1700
Data Index: 7478639 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4505. Min Act: -0.1700
Data Index: 5115719 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4667. Min Act: -0.1700
Data Index: 2780565 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4505. Min Act: -0.1700
Data Index: 7438524 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4342. Min Act: -0.1700
Data Index: 1141240 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4342. Min Act: -0.1700
Data Index: 6865907 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4016. Min Act: -0.1700
Data Index: 4902204 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6603. Min Range: -2.6603
Max Act: 2.4179. Min Act: -0.1700
Data Index: 7414132 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19