Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 339 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.3685. Min Act: -0.1700
Data Index: 2827943 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.1497. Min Act: -0.1700
Data Index: 4238430 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.0560. Min Act: -0.1700
Data Index: 2439326 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.0247. Min Act: -0.1700
Data Index: 7441320 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3685. Min Range: -5.3685
Max Act: 5.0247. Min Act: -0.1700
Data Index: 1266502 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.9310. Min Act: -0.1700
Data Index: 1783419 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8997. Min Act: -0.1700
Data Index: 1928280 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8997. Min Act: -0.1700
Data Index: 8713565 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8997. Min Act: -0.1700
Data Index: 7709192 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8685. Min Act: -0.1700
Data Index: 2830589 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8372. Min Act: -0.1700
Data Index: 710861 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8685. Min Act: -0.1700
Data Index: 4794788 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8685. Min Act: -0.1699
Data Index: 22476 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8372. Min Act: -0.1700
Data Index: 7686449 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8372. Min Act: -0.1700
Data Index: 4777646 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8372. Min Act: -0.1700
Data Index: 5402059 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8372. Min Act: -0.1700
Data Index: 4924503 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.7747. Min Act: -0.1700
Data Index: 270722 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8060. Min Act: -0.1700
Data Index: 6391432 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3685. Min Range: -5.3685
Max Act: 4.8060. Min Act: -0.1700
Data Index: 3225134 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19