Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.8788. Min Act: -0.1700
Data Index: 1403774 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.8788. Min Act: -0.1700
Data Index: 3596931 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.8788. Min Act: -0.1700
Data Index: 3277165 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.8788. Min Act: -0.1700
Data Index: 7024367 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.8163. Min Act: -0.1700
Data Index: 1479793 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.6601. Min Act: -0.1700
Data Index: 8185473 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5976. Min Act: -0.1700
Data Index: 4253029 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5976. Min Act: -0.1700
Data Index: 8162093 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5976. Min Act: -0.1700
Data Index: 3685226 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5351. Min Act: -0.1700
Data Index: 452745 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.4101. Min Act: -0.1700
Data Index: 4665933 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.4413. Min Act: -0.1700
Data Index: 3540934 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.3788. Min Act: -0.1700
Data Index: 1899043 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5351. Min Act: -0.1700
Data Index: 2732036 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.4413. Min Act: -0.1700
Data Index: 5572894 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.3476. Min Act: -0.1700
Data Index: 4712031 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.3476. Min Act: -0.1700
Data Index: 641980 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.4101. Min Act: -0.1700
Data Index: 5977715 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.3476. Min Act: -0.1700
Data Index: 1885471 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.3163. Min Act: -0.1700
Data Index: 1048645 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19