Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.4600. Min Act: -0.1700
Data Index: 5971303 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.4600. Min Act: -0.1700
Data Index: 7360177 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.4600. Min Act: -0.1700
Data Index: 2830196 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.4288. Min Act: -0.1700
Data Index: 6481775 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3975. Min Act: -0.1700
Data Index: 1460378 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3975. Min Act: -0.1700
Data Index: 661025 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3662. Min Act: -0.1700
Data Index: 129218 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3975. Min Act: -0.1700
Data Index: 6662692 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3662. Min Act: -0.1700
Data Index: 4753217 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3662. Min Act: -0.1700
Data Index: 7122576 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3662. Min Act: -0.1700
Data Index: 1460721 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3350. Min Act: -0.1700
Data Index: 4146572 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 5365419 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3350. Min Act: -0.1700
Data Index: 5106437 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3350. Min Act: -0.1700
Data Index: 3321422 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3350. Min Act: -0.1700
Data Index: 1452246 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 6697118 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 7195490 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.2725. Min Act: -0.1700
Data Index: 5755760 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.2725. Min Act: -0.1700
Data Index: 5515680 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19