Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 862 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.9612. Min Act: -0.1699
Data Index: 8548000 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.9102. Min Act: -0.1700
Data Index: 4862101 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8932. Min Act: -0.1700
Data Index: 5064244 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8761. Min Act: -0.1700
Data Index: 2322127 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8761. Min Act: -0.1700
Data Index: 6250372 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8590. Min Act: -0.1700
Data Index: 3192864 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8590. Min Act: -0.1700
Data Index: 197284 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8590. Min Act: -0.1700
Data Index: 802440 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8590. Min Act: -0.1700
Data Index: 1010508 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8590. Min Act: -0.1700
Data Index: 3701166 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8247. Min Act: -0.1700
Data Index: 1444879 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8075. Min Act: -0.1700
Data Index: 929256 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8075. Min Act: -0.1700
Data Index: 2803981 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.7903. Min Act: -0.1700
Data Index: 6800415 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8075. Min Act: -0.1700
Data Index: 2983994 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8247. Min Act: -0.1700
Data Index: 6606915 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.8247. Min Act: -0.1700
Data Index: 7176503 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.7731. Min Act: -0.1700
Data Index: 1760709 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.7903. Min Act: -0.1697
Data Index: 1812828 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9612. Min Range: -1.9612
Max Act: 1.7731. Min Act: -0.1700
Data Index: 925529 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19