Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1989 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.7752. Min Act: -0.1700
Data Index: 3727984 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.7752. Min Act: -0.1700
Data Index: 7555477 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.7752. Min Act: -0.1700
Data Index: 5774473 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.7440. Min Act: -0.1700
Data Index: 8797871 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.7440. Min Act: -0.1700
Data Index: 788585 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.7127. Min Act: -0.1700
Data Index: 1855528 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.6815. Min Act: -0.1700
Data Index: 3552428 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.6502. Min Act: -0.1700
Data Index: 2764520 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.6502. Min Act: -0.1700
Data Index: 145108 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.6190. Min Act: -0.1700
Data Index: 7116586 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.6502. Min Act: -0.1700
Data Index: 6130504 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.5877. Min Act: -0.1700
Data Index: 741149 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.5565. Min Act: -0.1700
Data Index: 7527627 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.5877. Min Act: -0.1700
Data Index: 4185934 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.5877. Min Act: -0.1700
Data Index: 175 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.5877. Min Act: -0.1700
Data Index: 304063 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.5877. Min Act: -0.1700
Data Index: 5831678 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.5877. Min Act: -0.1700
Data Index: 205709 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.5565. Min Act: -0.1700
Data Index: 4012075 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7752. Min Range: -5.7752
Max Act: 5.5565. Min Act: -0.1700
Data Index: 2487671 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19