Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6305 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2632. Min Range: -6.2632
Max Act: 6.2632. Min Act: -0.1700
Data Index: 5548452 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2632. Min Range: -6.2632
Max Act: 6.1070. Min Act: -0.1700
Data Index: 1534759 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2632. Min Range: -6.2632
Max Act: 6.1070. Min Act: -0.1700
Data Index: 1334321 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.8882. Min Act: -0.1700
Data Index: 4760145 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.7632. Min Act: -0.1700
Data Index: 2062333 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.7632. Min Act: -0.1700
Data Index: 7866257 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.7632. Min Act: -0.1700
Data Index: 4163400 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.7632. Min Act: -0.1700
Data Index: 2903831 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.7632. Min Act: -0.1700
Data Index: 2981643 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.7320. Min Act: -0.1700
Data Index: 7730032 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.6382. Min Act: -0.1700
Data Index: 715257 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.6070. Min Act: -0.1700
Data Index: 8479798 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.6070. Min Act: -0.1700
Data Index: 3381133 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.5757. Min Act: -0.1700
Data Index: 4670751 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.5757. Min Act: -0.1700
Data Index: 8734123 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.5445. Min Act: -0.1700
Data Index: 2847400 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.5445. Min Act: -0.1700
Data Index: 1525246 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.4820. Min Act: -0.1700
Data Index: 747521 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.4820. Min Act: -0.1700
Data Index: 2313476 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2632. Min Range: -6.2632
Max Act: 5.4507. Min Act: -0.1700
Data Index: 973769 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19