Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2576 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0484. Min Range: -6.0484
Max Act: 6.0484. Min Act: -0.1700
Data Index: 3926185 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0484. Min Range: -6.0484
Max Act: 6.0171. Min Act: -0.1700
Data Index: 7040899 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9859. Min Act: -0.1700
Data Index: 1631103 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9234. Min Act: -0.1700
Data Index: 4606168 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9234. Min Act: -0.1700
Data Index: 2815937 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9234. Min Act: -0.1700
Data Index: 1161665 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9234. Min Act: -0.1700
Data Index: 5576269 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.8921. Min Act: -0.1700
Data Index: 2595957 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9234. Min Act: -0.1700
Data Index: 7031656 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.8921. Min Act: -0.1700
Data Index: 6179236 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9546. Min Act: -0.1700
Data Index: 2974246 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9234. Min Act: -0.1700
Data Index: 1655393 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.8921. Min Act: -0.1700
Data Index: 5638158 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.8921. Min Act: -0.1700
Data Index: 3373104 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.8921. Min Act: -0.1700
Data Index: 7687298 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9234. Min Act: -0.1700
Data Index: 7691180 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.9234. Min Act: -0.1700
Data Index: 5384076 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.8921. Min Act: -0.1700
Data Index: 2067826 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.8921. Min Act: -0.1700
Data Index: 1850532 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0484. Min Range: -6.0484
Max Act: 5.8609. Min Act: -0.1700
Data Index: 3676015 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19