Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2188 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3826. Min Range: -8.3826
Max Act: 8.3826. Min Act: -0.1700
Data Index: 4741225 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3826. Min Range: -8.3826
Max Act: 8.0076. Min Act: -0.1700
Data Index: 4637591 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3826. Min Range: -8.3826
Max Act: 8.0076. Min Act: -0.1700
Data Index: 4876216 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.9451. Min Act: -0.1700
Data Index: 6750839 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.8201. Min Act: -0.1700
Data Index: 1753568 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.8201. Min Act: -0.1700
Data Index: 1894221 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.7576. Min Act: -0.1700
Data Index: 3655694 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.7576. Min Act: -0.1700
Data Index: 7747429 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.7576. Min Act: -0.1700
Data Index: 7521676 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.7576. Min Act: -0.1700
Data Index: 6033427 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.7576. Min Act: -0.1700
Data Index: 3862111 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.8201. Min Act: -0.1700
Data Index: 4638022 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.7576. Min Act: -0.1700
Data Index: 2511018 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.6326. Min Act: -0.1700
Data Index: 4086509 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.6951. Min Act: -0.1700
Data Index: 4738566 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.6951. Min Act: -0.1700
Data Index: 4975573 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.6951. Min Act: -0.1700
Data Index: 2874190 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.6951. Min Act: -0.1700
Data Index: 3471313 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.6326. Min Act: -0.1700
Data Index: 4344507 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3826. Min Range: -8.3826
Max Act: 7.6326. Min Act: -0.1700
Data Index: 1729290 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19