Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 389 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9488. Min Range: -10.9488
Max Act: 10.9488. Min Act: -0.1700
Data Index: 1177952 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9488. Min Range: -10.9488
Max Act: 10.6988. Min Act: -0.1700
Data Index: 6887390 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9488. Min Range: -10.9488
Max Act: 10.5113. Min Act: -0.1700
Data Index: 1591532 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9488. Min Range: -10.9488
Max Act: 10.0738. Min Act: -0.1700
Data Index: 4564815 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9488. Min Range: -10.9488
Max Act: 10.1988. Min Act: -0.1700
Data Index: 6565654 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9488. Min Range: -10.9488
Max Act: 10.0738. Min Act: -0.1700
Data Index: 1644143 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9488. Min Range: -10.9488
Max Act: 10.0738. Min Act: -0.1700
Data Index: 7417904 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9488. Min Range: -10.9488
Max Act: 10.0113. Min Act: -0.1700
Data Index: 1281802 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.8863. Min Act: -0.1700
Data Index: 6692431 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.8863. Min Act: -0.1700
Data Index: 4564803 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9488. Min Range: -10.9488
Max Act: 10.0113. Min Act: -0.1700
Data Index: 2025568 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.9488. Min Act: -0.1700
Data Index: 4580472 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.8863. Min Act: -0.1700
Data Index: 6628280 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.9488. Min Act: -0.1700
Data Index: 7125814 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.8863. Min Act: -0.1700
Data Index: 5970145 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.8238. Min Act: -0.1700
Data Index: 2775192 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.7613. Min Act: -0.1700
Data Index: 5667546 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.8238. Min Act: -0.1700
Data Index: 7536641 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.8238. Min Act: -0.1700
Data Index: 8023896 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9488. Min Range: -10.9488
Max Act: 9.7613. Min Act: -0.1700
Data Index: 5206096 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19