Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1005 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.3936. Min Act: -0.1700
Data Index: 5732187 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.4561. Min Act: -0.1700
Data Index: 3355137 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.3936. Min Act: -0.1700
Data Index: 1484938 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.3936. Min Act: -0.1700
Data Index: 8724408 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.3311. Min Act: -0.1700
Data Index: 7032481 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.3311. Min Act: -0.1700
Data Index: 4027705 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.3311. Min Act: -0.1700
Data Index: 7349681 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.2686. Min Act: -0.1700
Data Index: 7969068 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.2686. Min Act: -0.1700
Data Index: 4635129 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.2061. Min Act: -0.1700
Data Index: 2497212 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.2061. Min Act: -0.1700
Data Index: 3681530 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.1748. Min Act: -0.1700
Data Index: 4947972 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.2373. Min Act: -0.1700
Data Index: 5922681 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.2061. Min Act: -0.1700
Data Index: 6060941 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.2061. Min Act: -0.1700
Data Index: 3851636 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.2061. Min Act: -0.1700
Data Index: 7191739 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.1748. Min Act: -0.1700
Data Index: 7263414 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.1748. Min Act: -0.1700
Data Index: 1871696 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.1436. Min Act: -0.1700
Data Index: 2234427 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4561. Min Range: -6.4561
Max Act: 6.1748. Min Act: -0.1700
Data Index: 7346652 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19