Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4307. Min Range: -6.4307
Max Act: 6.4307. Min Act: -0.1700
Data Index: 6721028 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4307. Min Range: -6.4307
Max Act: 6.3369. Min Act: -0.1700
Data Index: 3168113 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4307. Min Range: -6.4307
Max Act: 6.2744. Min Act: -0.1700
Data Index: 4868147 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4307. Min Range: -6.4307
Max Act: 6.1494. Min Act: -0.1700
Data Index: 1272159 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4307. Min Range: -6.4307
Max Act: 6.0557. Min Act: -0.1700
Data Index: 2643418 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4307. Min Range: -6.4307
Max Act: 6.0557. Min Act: -0.1700
Data Index: 79113 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4307. Min Range: -6.4307
Max Act: 6.0557. Min Act: -0.1700
Data Index: 7445896 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4307. Min Range: -6.4307
Max Act: 6.0244. Min Act: -0.1700
Data Index: 5895508 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.9932. Min Act: -0.1700
Data Index: 1449820 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.9932. Min Act: -0.1700
Data Index: 6118387 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.9619. Min Act: -0.1700
Data Index: 5763080 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.9619. Min Act: -0.1700
Data Index: 2850732 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.9307. Min Act: -0.1700
Data Index: 7552635 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.8994. Min Act: -0.1700
Data Index: 2064755 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.8994. Min Act: -0.1700
Data Index: 1941729 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.8994. Min Act: -0.1700
Data Index: 1050766 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.8682. Min Act: -0.1700
Data Index: 2696163 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.8369. Min Act: -0.1700
Data Index: 2696164 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.8057. Min Act: -0.1700
Data Index: 3559717 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4307. Min Range: -6.4307
Max Act: 5.8369. Min Act: -0.1700
Data Index: 1871576 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19