Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1853 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5968. Min Act: -0.1700
Data Index: 2400080 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5031. Min Act: -0.1700
Data Index: 1703643 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.2843. Min Act: -0.1700
Data Index: 6277727 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.2218. Min Act: -0.1700
Data Index: 6895526 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.2218. Min Act: -0.1700
Data Index: 2945578 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.1906. Min Act: -0.1700
Data Index: 5524205 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.1906. Min Act: -0.1700
Data Index: 1872628 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.1593. Min Act: -0.1700
Data Index: 8453751 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.1281. Min Act: -0.1700
Data Index: 5041049 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.1281. Min Act: -0.1700
Data Index: 7421762 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.0968. Min Act: -0.1700
Data Index: 1026261 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.1281. Min Act: -0.1700
Data Index: 4145498 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.0968. Min Act: -0.1700
Data Index: 8277171 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.0656. Min Act: -0.1700
Data Index: 6524125 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.0656. Min Act: -0.1700
Data Index: 3325457 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.0343. Min Act: -0.1700
Data Index: 5154119 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.0656. Min Act: -0.1700
Data Index: 1170891 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.0031. Min Act: -0.1699
Data Index: 5399582 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.0031. Min Act: -0.1700
Data Index: 60385 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5968. Min Range: -5.5968
Max Act: 4.9718. Min Act: -0.1700
Data Index: 5570157 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19