Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1944 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.8718. Min Act: -0.1700
Data Index: 5392122 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.8406. Min Act: -0.1700
Data Index: 7944206 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.7468. Min Act: -0.1700
Data Index: 2627227 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.6531. Min Act: -0.1700
Data Index: 3026941 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.6531. Min Act: -0.1700
Data Index: 2363505 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.5906. Min Act: -0.1700
Data Index: 5258845 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.6218. Min Act: -0.1700
Data Index: 5102266 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.6218. Min Act: -0.1700
Data Index: 2909718 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.5906. Min Act: -0.1700
Data Index: 8571605 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.5593. Min Act: -0.1700
Data Index: 6446775 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4968. Min Act: -0.1700
Data Index: 3204200 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4968. Min Act: -0.1700
Data Index: 3273889 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4968. Min Act: -0.1700
Data Index: 2651599 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4656. Min Act: -0.1700
Data Index: 8629922 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4656. Min Act: -0.1700
Data Index: 4693017 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4343. Min Act: -0.1700
Data Index: 5410438 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4343. Min Act: -0.1700
Data Index: 8033099 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4343. Min Act: -0.1700
Data Index: 1353525 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4343. Min Act: -0.1700
Data Index: 6824655 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8718. Min Range: -5.8718
Max Act: 5.4343. Min Act: -0.1700
Data Index: 802526 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19