Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0559. Min Range: -8.0559
Max Act: 8.0559. Min Act: -0.1700
Data Index: 2159284 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.9309. Min Act: -0.1700
Data Index: 8529848 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.6809. Min Act: -0.1700
Data Index: 7535040 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.6809. Min Act: -0.1700
Data Index: 8217073 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.6184. Min Act: -0.1700
Data Index: 7261656 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.5559. Min Act: -0.1700
Data Index: 6836112 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.4622. Min Act: -0.1700
Data Index: 1599242 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.4622. Min Act: -0.1700
Data Index: 3889646 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.3997. Min Act: -0.1700
Data Index: 5552869 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.3684. Min Act: -0.1700
Data Index: 3585444 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.3997. Min Act: -0.1700
Data Index: 753736 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.3059. Min Act: -0.1700
Data Index: 2146725 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.3059. Min Act: -0.1700
Data Index: 879667 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.2747. Min Act: -0.1700
Data Index: 978450 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.2434. Min Act: -0.1700
Data Index: 4955243 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.2434. Min Act: -0.1700
Data Index: 5741802 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.2434. Min Act: -0.1700
Data Index: 3933167 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.2122. Min Act: -0.1700
Data Index: 5398242 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.2122. Min Act: -0.1700
Data Index: 4683866 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0559. Min Range: -8.0559
Max Act: 7.1809. Min Act: -0.1700
Data Index: 7668773 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19