Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4773 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0568. Min Range: -6.0568
Max Act: 6.0568. Min Act: -0.1700
Data Index: 6544541 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.7755. Min Act: -0.1700
Data Index: 1105565 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.7755. Min Act: -0.1700
Data Index: 2563588 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.7755. Min Act: -0.1700
Data Index: 4535787 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.7130. Min Act: -0.1700
Data Index: 22797 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.6818. Min Act: -0.1700
Data Index: 5560725 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.6818. Min Act: -0.1700
Data Index: 1882714 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.6818. Min Act: -0.1700
Data Index: 2126903 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.6505. Min Act: -0.1700
Data Index: 6375388 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.6505. Min Act: -0.1700
Data Index: 6601280 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.6505. Min Act: -0.1700
Data Index: 993875 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.6505. Min Act: -0.1700
Data Index: 4521906 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.6193. Min Act: -0.1700
Data Index: 8724786 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.6193. Min Act: -0.1700
Data Index: 8306848 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.5880. Min Act: -0.1700
Data Index: 2750230 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.5880. Min Act: -0.1700
Data Index: 8432989 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.5568. Min Act: -0.1700
Data Index: 2941805 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.5568. Min Act: -0.1700
Data Index: 7407846 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.5255. Min Act: -0.1700
Data Index: 2022651 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0568. Min Range: -6.0568
Max Act: 5.5255. Min Act: -0.1700
Data Index: 8288403 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19