Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.9107. Min Act: -0.1700
Data Index: 1590871 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.5357. Min Act: -0.1700
Data Index: 6502859 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.5044. Min Act: -0.1700
Data Index: 5861373 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.4732. Min Act: -0.1700
Data Index: 3086263 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.4419. Min Act: -0.1700
Data Index: 8044768 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.3794. Min Act: -0.1700
Data Index: 4928061 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.3794. Min Act: -0.1700
Data Index: 5654315 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.3794. Min Act: -0.1700
Data Index: 2507303 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.3794. Min Act: -0.1700
Data Index: 1687672 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.3169. Min Act: -0.1700
Data Index: 316319 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.3169. Min Act: -0.1700
Data Index: 3109939 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.2857. Min Act: -0.1700
Data Index: 7477232 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.3169. Min Act: -0.1700
Data Index: 5879539 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.3169. Min Act: -0.1700
Data Index: 2035662 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.2857. Min Act: -0.1700
Data Index: 6104966 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.2857. Min Act: -0.1700
Data Index: 3623830 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.3169. Min Act: -0.1700
Data Index: 1161761 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.2857. Min Act: -0.1700
Data Index: 1895923 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.2544. Min Act: -0.1700
Data Index: 403820 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9107. Min Range: -4.9107
Max Act: 4.2544. Min Act: -0.1700
Data Index: 1460636 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19