Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.5330. Min Act: -0.1700
Data Index: 256820 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.4393. Min Act: -0.1700
Data Index: 5782994 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.4080. Min Act: -0.1700
Data Index: 4123077 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.3768. Min Act: -0.1700
Data Index: 3592545 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.3143. Min Act: -0.1700
Data Index: 3538907 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.3455. Min Act: -0.1700
Data Index: 1136634 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.3143. Min Act: -0.1700
Data Index: 2914586 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.2518. Min Act: -0.1700
Data Index: 8600538 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.2830. Min Act: -0.1700
Data Index: 4853383 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.2518. Min Act: -0.1700
Data Index: 4158531 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.2830. Min Act: -0.1700
Data Index: 6291330 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.2830. Min Act: -0.1700
Data Index: 7380708 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.1893. Min Act: -0.1700
Data Index: 7403699 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.2205. Min Act: -0.1700
Data Index: 4743555 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.1893. Min Act: -0.1700
Data Index: 1151986 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.1580. Min Act: -0.1700
Data Index: 1980938 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.1893. Min Act: -0.1700
Data Index: 2341190 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.1580. Min Act: -0.1700
Data Index: 3592560 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.1580. Min Act: -0.1700
Data Index: 3750940 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5330. Min Range: -5.5330
Max Act: 5.1268. Min Act: -0.1700
Data Index: 2395838 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19