Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1986 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.6700. Min Act: -0.1700
Data Index: 968421 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.6700. Min Act: -0.1700
Data Index: 7798014 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.6543. Min Act: -0.1700
Data Index: 6667967 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.6387. Min Act: -0.1700
Data Index: 7957468 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.6074. Min Act: -0.1700
Data Index: 554330 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.5604. Min Act: -0.1700
Data Index: 8137711 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.4821. Min Act: -0.1700
Data Index: 6114191 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.4351. Min Act: -0.1700
Data Index: 1648094 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.4038. Min Act: -0.1700
Data Index: 7685719 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3567. Min Act: -0.1700
Data Index: 7161744 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3410. Min Act: -0.1700
Data Index: 2253152 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3410. Min Act: -0.1700
Data Index: 4048783 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3724. Min Act: -0.1700
Data Index: 3757088 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3410. Min Act: -0.1700
Data Index: 8318021 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3410. Min Act: -0.1700
Data Index: 1714705 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3410. Min Act: -0.1700
Data Index: 4042906 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3254. Min Act: -0.1700
Data Index: 8618634 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3254. Min Act: -0.1700
Data Index: 1616683 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3410. Min Act: -0.1700
Data Index: 3468336 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6700. Min Range: -3.6700
Max Act: 3.3097. Min Act: -0.1700
Data Index: 8367068 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19