Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.1123. Min Act: -0.1699
Data Index: 1985317 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0283. Min Act: -0.1700
Data Index: 6133790 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0283. Min Act: -0.1700
Data Index: 7284033 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0451. Min Act: -0.1700
Data Index: 3917538 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0451. Min Act: -0.1700
Data Index: 756296 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0283. Min Act: -0.1700
Data Index: 4561783 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0114. Min Act: -0.1695
Data Index: 7798554 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0283. Min Act: -0.1700
Data Index: 4997050 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0114. Min Act: -0.1700
Data Index: 8399030 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0114. Min Act: -0.1700
Data Index: 2567425 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0114. Min Act: -0.1700
Data Index: 7821895 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1123. Min Range: -2.1123
Max Act: 1.9945. Min Act: -0.1700
Data Index: 5417467 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0114. Min Act: -0.1700
Data Index: 1979888 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0114. Min Act: -0.1700
Data Index: 1248275 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1123. Min Range: -2.1123
Max Act: 2.0114. Min Act: -0.1700
Data Index: 1733569 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1123. Min Range: -2.1123
Max Act: 1.9945. Min Act: -0.1700
Data Index: 1643886 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1123. Min Range: -2.1123
Max Act: 1.9776. Min Act: -0.1700
Data Index: 5417471 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1123. Min Range: -2.1123
Max Act: 1.9776. Min Act: -0.1700
Data Index: 5585427 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1123. Min Range: -2.1123
Max Act: 1.9945. Min Act: -0.1700
Data Index: 2732045 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1123. Min Range: -2.1123
Max Act: 1.9945. Min Act: -0.1700
Data Index: 6780567 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19