Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1140 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.7186. Min Act: -0.1700
Data Index: 1261045 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.7499. Min Act: -0.1700
Data Index: 3574445 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.7186. Min Act: -0.1700
Data Index: 5957809 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.6560. Min Act: -0.1700
Data Index: 2350383 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.6873. Min Act: -0.1700
Data Index: 8621856 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.6247. Min Act: -0.1700
Data Index: 5445807 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.6873. Min Act: -0.1700
Data Index: 5668747 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.5934. Min Act: -0.1700
Data Index: 3105382 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.5934. Min Act: -0.1700
Data Index: 74174 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.6247. Min Act: -0.1700
Data Index: 2040843 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.5621. Min Act: -0.1700
Data Index: 1121905 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.5934. Min Act: -0.1700
Data Index: 2172797 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.5621. Min Act: -0.1700
Data Index: 6846553 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.5308. Min Act: -0.1700
Data Index: 1837133 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.5621. Min Act: -0.1700
Data Index: 1582094 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.4995. Min Act: -0.1700
Data Index: 7283800 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.4995. Min Act: -0.1700
Data Index: 8348040 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.4995. Min Act: -0.1700
Data Index: 4675615 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.5621. Min Act: -0.1700
Data Index: 8371458 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7499. Min Range: -3.7499
Max Act: 3.4995. Min Act: -0.1700
Data Index: 4732481 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19