Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1507 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.8601. Min Act: -0.1700
Data Index: 685728 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.8601. Min Act: -0.1700
Data Index: 3957006 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7976. Min Act: -0.1700
Data Index: 7631662 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7976. Min Act: -0.1700
Data Index: 7605513 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7663. Min Act: -0.1700
Data Index: 1010518 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7663. Min Act: -0.1700
Data Index: 6560113 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7351. Min Act: -0.1700
Data Index: 3207125 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7351. Min Act: -0.1700
Data Index: 5843203 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7351. Min Act: -0.1700
Data Index: 5869601 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7351. Min Act: -0.1700
Data Index: 5250756 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7351. Min Act: -0.1700
Data Index: 6195666 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7038. Min Act: -0.1700
Data Index: 5900924 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7038. Min Act: -0.1700
Data Index: 3458192 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7038. Min Act: -0.1700
Data Index: 7049217 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7038. Min Act: -0.1700
Data Index: 902223 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.7038. Min Act: -0.1700
Data Index: 880880 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.6726. Min Act: -0.1700
Data Index: 3943932 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.6726. Min Act: -0.1700
Data Index: 6279667 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.6726. Min Act: -0.1700
Data Index: 4492865 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8601. Min Range: -4.8601
Max Act: 4.6726. Min Act: -0.1700
Data Index: 2559837 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19