Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5656. Min Range: -9.5656
Max Act: 9.5656. Min Act: -0.1700
Data Index: 3509435 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5656. Min Range: -9.5656
Max Act: 9.3156. Min Act: -0.1700
Data Index: 1123461 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5656. Min Range: -9.5656
Max Act: 9.2531. Min Act: -0.1700
Data Index: 175761 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5656. Min Range: -9.5656
Max Act: 9.1281. Min Act: -0.1700
Data Index: 4706064 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5656. Min Range: -9.5656
Max Act: 9.1281. Min Act: -0.1700
Data Index: 6486506 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5656. Min Range: -9.5656
Max Act: 9.0656. Min Act: -0.1700
Data Index: 5218780 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.8781. Min Act: -0.1700
Data Index: 1905647 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.8781. Min Act: -0.1700
Data Index: 23593 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.8781. Min Act: -0.1700
Data Index: 1777370 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.8156. Min Act: -0.1700
Data Index: 5148186 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.7531. Min Act: -0.1700
Data Index: 7399632 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.7531. Min Act: -0.1700
Data Index: 2314572 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.8156. Min Act: -0.1700
Data Index: 1762232 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.6906. Min Act: -0.1700
Data Index: 3134809 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.6906. Min Act: -0.1700
Data Index: 1304927 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.6906. Min Act: -0.1700
Data Index: 4594672 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.6906. Min Act: -0.1700
Data Index: 2953419 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.6906. Min Act: -0.1700
Data Index: 5318399 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.6906. Min Act: -0.1700
Data Index: 1900287 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5656. Min Range: -9.5656
Max Act: 8.6906. Min Act: -0.1700
Data Index: 5437525 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19