Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4368 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0481. Min Range: -3.0481
Max Act: 3.0481. Min Act: -0.1700
Data Index: 7505270 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0481. Min Range: -3.0481
Max Act: 3.0481. Min Act: -0.1700
Data Index: 6691512 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0481. Min Range: -3.0481
Max Act: 3.0323. Min Act: -0.1700
Data Index: 7560656 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0481. Min Range: -3.0481
Max Act: 3.0165. Min Act: -0.1700
Data Index: 1470168 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0481. Min Range: -3.0481
Max Act: 3.0007. Min Act: -0.1700
Data Index: 4487056 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9849. Min Act: -0.1700
Data Index: 3321057 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0481. Min Range: -3.0481
Max Act: 3.0007. Min Act: -0.1700
Data Index: 1293871 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9691. Min Act: -0.1700
Data Index: 1600967 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9533. Min Act: -0.1700
Data Index: 1267933 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9533. Min Act: -0.1700
Data Index: 5301659 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9374. Min Act: -0.1700
Data Index: 5610015 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9533. Min Act: -0.1700
Data Index: 1784386 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9374. Min Act: -0.1700
Data Index: 5153917 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9216. Min Act: -0.1700
Data Index: 7627291 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9374. Min Act: -0.1700
Data Index: 7316054 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9216. Min Act: -0.1700
Data Index: 4148155 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9216. Min Act: -0.1700
Data Index: 4284244 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9057. Min Act: -0.1700
Data Index: 703266 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9057. Min Act: -0.1700
Data Index: 8028689 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0481. Min Range: -3.0481
Max Act: 2.9057. Min Act: -0.1700
Data Index: 3901721 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19