Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5780 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0282. Min Range: -9.0282
Max Act: 9.0282. Min Act: -0.1700
Data Index: 4448671 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0282. Min Range: -9.0282
Max Act: 9.0282. Min Act: -0.1700
Data Index: 6740922 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7782. Min Act: -0.1700
Data Index: 2657289 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7782. Min Act: -0.1700
Data Index: 8540627 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7782. Min Act: -0.1700
Data Index: 6039852 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7157. Min Act: -0.1700
Data Index: 4630791 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7157. Min Act: -0.1700
Data Index: 3626393 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7157. Min Act: -0.1700
Data Index: 4600039 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7157. Min Act: -0.1700
Data Index: 646846 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7157. Min Act: -0.1700
Data Index: 6333341 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7157. Min Act: -0.1700
Data Index: 3575845 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.7157. Min Act: -0.1700
Data Index: 4912564 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.6532. Min Act: -0.1700
Data Index: 4449236 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.6532. Min Act: -0.1700
Data Index: 1788150 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.6532. Min Act: -0.1700
Data Index: 7015410 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.6532. Min Act: -0.1700
Data Index: 8772856 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.5907. Min Act: -0.1700
Data Index: 6398365 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.5907. Min Act: -0.1700
Data Index: 1057121 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.5907. Min Act: -0.1700
Data Index: 6771235 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0282. Min Range: -9.0282
Max Act: 8.5907. Min Act: -0.1700
Data Index: 5014544 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19