Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1992. Min Range: -6.1992
Max Act: 6.1992. Min Act: -0.1700
Data Index: 6387956 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1992. Min Range: -6.1992
Max Act: 6.1367. Min Act: -0.1700
Data Index: 2830325 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1992. Min Range: -6.1992
Max Act: 6.1367. Min Act: -0.1700
Data Index: 922015 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1992. Min Range: -6.1992
Max Act: 6.0117. Min Act: -0.1700
Data Index: 7900402 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.9179. Min Act: -0.1700
Data Index: 1474767 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.9179. Min Act: -0.1700
Data Index: 864940 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.8867. Min Act: -0.1700
Data Index: 1303646 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.8554. Min Act: -0.1700
Data Index: 7584237 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.8867. Min Act: -0.1700
Data Index: 1627204 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.8554. Min Act: -0.1700
Data Index: 5969825 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.8554. Min Act: -0.1700
Data Index: 1474766 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.7929. Min Act: -0.1700
Data Index: 1303644 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.7929. Min Act: -0.1700
Data Index: 2296903 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.7617. Min Act: -0.1700
Data Index: 1230029 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.7617. Min Act: -0.1700
Data Index: 3915274 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.7929. Min Act: -0.1700
Data Index: 6216532 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.7617. Min Act: -0.1700
Data Index: 4875591 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.7929. Min Act: -0.1700
Data Index: 7225272 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.7617. Min Act: -0.1700
Data Index: 5825516 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1992. Min Range: -6.1992
Max Act: 5.7617. Min Act: -0.1700
Data Index: 4309260 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19