Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.3088. Min Act: -0.1700
Data Index: 3579449 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.2463. Min Act: -0.1700
Data Index: 999755 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.1838. Min Act: -0.1700
Data Index: 7773845 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.1213. Min Act: -0.1700
Data Index: 1292280 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.1213. Min Act: -0.1700
Data Index: 4256439 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.0900. Min Act: -0.1700
Data Index: 5119508 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.0900. Min Act: -0.1700
Data Index: 787117 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.0588. Min Act: -0.1700
Data Index: 3833072 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.0588. Min Act: -0.1700
Data Index: 3356338 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.0275. Min Act: -0.1700
Data Index: 5956815 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3088. Min Range: -5.3088
Max Act: 4.9650. Min Act: -0.1700
Data Index: 5758264 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3088. Min Range: -5.3088
Max Act: 5.0275. Min Act: -0.1700
Data Index: 6434125 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3088. Min Range: -5.3088
Max Act: 4.9650. Min Act: -0.1700
Data Index: 1737057 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3088. Min Range: -5.3088
Max Act: 4.9650. Min Act: -0.1700
Data Index: 6832580 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3088. Min Range: -5.3088
Max Act: 4.9338. Min Act: -0.1700
Data Index: 1537643 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3088. Min Range: -5.3088
Max Act: 4.9025. Min Act: -0.1700
Data Index: 3348447 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3088. Min Range: -5.3088
Max Act: 4.9338. Min Act: -0.1700
Data Index: 7229463 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3088. Min Range: -5.3088
Max Act: 4.9025. Min Act: -0.1700
Data Index: 1372440 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3088. Min Range: -5.3088
Max Act: 4.8713. Min Act: -0.1700
Data Index: 6068492 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3088. Min Range: -5.3088
Max Act: 4.8713. Min Act: -0.1700
Data Index: 3727697 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19