Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5288 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.3537. Min Act: -0.1700
Data Index: 433105 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.2287. Min Act: -0.1700
Data Index: 4385659 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.2287. Min Act: -0.1700
Data Index: 5006915 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1662. Min Act: -0.1700
Data Index: 5163982 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1662. Min Act: -0.1700
Data Index: 3657038 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1350. Min Act: -0.1700
Data Index: 6246492 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1350. Min Act: -0.1700
Data Index: 6281016 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.1037. Min Act: -0.1700
Data Index: 5880899 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0725. Min Act: -0.1700
Data Index: 8363156 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0725. Min Act: -0.1700
Data Index: 694363 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0412. Min Act: -0.1700
Data Index: 6711305 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0412. Min Act: -0.1700
Data Index: 1563017 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0100. Min Act: -0.1700
Data Index: 6936960 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3537. Min Range: -6.3537
Max Act: 6.0100. Min Act: -0.1700
Data Index: 1369519 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3537. Min Range: -6.3537
Max Act: 5.9787. Min Act: -0.1700
Data Index: 8649610 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3537. Min Range: -6.3537
Max Act: 5.9787. Min Act: -0.1700
Data Index: 7553827 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3537. Min Range: -6.3537
Max Act: 5.9787. Min Act: -0.1700
Data Index: 3229306 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3537. Min Range: -6.3537
Max Act: 5.9475. Min Act: -0.1700
Data Index: 623680 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3537. Min Range: -6.3537
Max Act: 5.9475. Min Act: -0.1700
Data Index: 7728673 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3537. Min Range: -6.3537
Max Act: 5.9475. Min Act: -0.1700
Data Index: 2094226 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19