Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2662 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.8918. Min Act: -0.1700
Data Index: 4597495 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.8293. Min Act: -0.1700
Data Index: 1924898 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.8293. Min Act: -0.1700
Data Index: 5300129 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.8293. Min Act: -0.1700
Data Index: 3031801 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7980. Min Act: -0.1700
Data Index: 6548842 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.8293. Min Act: -0.1700
Data Index: 3766581 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7980. Min Act: -0.1700
Data Index: 7969027 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7668. Min Act: -0.1700
Data Index: 2937117 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7668. Min Act: -0.1700
Data Index: 1850493 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7668. Min Act: -0.1700
Data Index: 5789132 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7668. Min Act: -0.1700
Data Index: 2468456 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7043. Min Act: -0.1700
Data Index: 2268474 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7043. Min Act: -0.1700
Data Index: 4387553 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7043. Min Act: -0.1700
Data Index: 5822223 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7043. Min Act: -0.1700
Data Index: 4507267 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.6730. Min Act: -0.1700
Data Index: 2549556 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.6730. Min Act: -0.1700
Data Index: 4930550 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.6730. Min Act: -0.1700
Data Index: 186659 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7043. Min Act: -0.1700
Data Index: 380673 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.6730. Min Act: -0.1700
Data Index: 1371251 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19