Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0666. Min Range: -5.0666
Max Act: 5.0666. Min Act: -0.1700
Data Index: 3508002 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0666. Min Range: -5.0666
Max Act: 5.0354. Min Act: -0.1700
Data Index: 4397790 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9729. Min Act: -0.1700
Data Index: 2751507 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9416. Min Act: -0.1700
Data Index: 4043567 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9416. Min Act: -0.1700
Data Index: 3508003 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9416. Min Act: -0.1700
Data Index: 7516353 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 5534171 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 5603574 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.9104. Min Act: -0.1700
Data Index: 8238595 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8479. Min Act: -0.1700
Data Index: 7380704 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 4397795 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 5127821 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 798298 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 4164863 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 2428667 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 3991438 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8791. Min Act: -0.1700
Data Index: 3234820 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8479. Min Act: -0.1700
Data Index: 4068541 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8479. Min Act: -0.1700
Data Index: 714973 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0666. Min Range: -5.0666
Max Act: 4.8479. Min Act: -0.1700
Data Index: 6023240 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19