Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 455 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0351. Min Range: -7.0351
Max Act: 7.0351. Min Act: -0.1700
Data Index: 5380603 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.9413. Min Act: -0.1700
Data Index: 6692380 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.7851. Min Act: -0.1700
Data Index: 338614 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.7538. Min Act: -0.1700
Data Index: 8705147 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.6913. Min Act: -0.1700
Data Index: 5044657 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.6601. Min Act: -0.1700
Data Index: 4550410 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.6913. Min Act: -0.1700
Data Index: 1469946 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.6913. Min Act: -0.1700
Data Index: 3909989 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.6288. Min Act: -0.1700
Data Index: 972662 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.5976. Min Act: -0.1700
Data Index: 6523998 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.5663. Min Act: -0.1700
Data Index: 3868261 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.5663. Min Act: -0.1700
Data Index: 7825570 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.5351. Min Act: -0.1700
Data Index: 928161 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.5351. Min Act: -0.1700
Data Index: 8706619 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.5038. Min Act: -0.1700
Data Index: 3142759 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.4726. Min Act: -0.1700
Data Index: 6080854 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.4726. Min Act: -0.1700
Data Index: 6949144 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.4726. Min Act: -0.1700
Data Index: 4299282 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.4726. Min Act: -0.1700
Data Index: 1384619 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0351. Min Range: -7.0351
Max Act: 6.4413. Min Act: -0.1700
Data Index: 5492253 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19