Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1106 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.6674. Min Act: -0.1700
Data Index: 3322921 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3549. Min Act: -0.1700
Data Index: 1899213 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3549. Min Act: -0.1700
Data Index: 7315380 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3549. Min Act: -0.1700
Data Index: 8402525 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2924. Min Act: -0.1700
Data Index: 6327696 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.3236. Min Act: -0.1700
Data Index: 3389386 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6035055 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6162395 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6794114 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6918585 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1986. Min Act: -0.1700
Data Index: 666573 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1986. Min Act: -0.1700
Data Index: 1312502 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1986. Min Act: -0.1700
Data Index: 5560490 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1674. Min Act: -0.1700
Data Index: 7282040 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1674. Min Act: -0.1700
Data Index: 2111982 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1361. Min Act: -0.1700
Data Index: 4430860 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1361. Min Act: -0.1700
Data Index: 1238466 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1361. Min Act: -0.1700
Data Index: 4082357 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1049. Min Act: -0.1700
Data Index: 5438504 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6674. Min Range: -5.6674
Max Act: 5.1049. Min Act: -0.1700
Data Index: 4449200 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19