Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5831 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0464. Min Range: -4.0464
Max Act: 4.0464. Min Act: -0.1700
Data Index: 7086798 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.9213. Min Act: -0.1700
Data Index: 5005708 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.8901. Min Act: -0.1700
Data Index: 6768662 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.8588. Min Act: -0.1700
Data Index: 3911970 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.8275. Min Act: -0.1700
Data Index: 6371714 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.7963. Min Act: -0.1700
Data Index: 1997667 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.7963. Min Act: -0.1700
Data Index: 8109786 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.7337. Min Act: -0.1700
Data Index: 1965970 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6711. Min Act: -0.1700
Data Index: 6197497 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6711. Min Act: -0.1700
Data Index: 8051399 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6555. Min Act: -0.1700
Data Index: 4287891 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6398. Min Act: -0.1700
Data Index: 3842751 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6398. Min Act: -0.1700
Data Index: 6245415 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6398. Min Act: -0.1700
Data Index: 3066279 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6398. Min Act: -0.1700
Data Index: 7248091 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6085. Min Act: -0.1700
Data Index: 2637409 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6242. Min Act: -0.1700
Data Index: 6667193 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.5929. Min Act: -0.1700
Data Index: 5244266 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.6242. Min Act: -0.1700
Data Index: 7982754 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0464. Min Range: -4.0464
Max Act: 3.5929. Min Act: -0.1700
Data Index: 6005039 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19