Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 829 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.3484. Min Act: -0.1700
Data Index: 181013 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2859. Min Act: -0.1700
Data Index: 7279199 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2859. Min Act: -0.1700
Data Index: 907704 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2546. Min Act: -0.1700
Data Index: 2801816 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2859. Min Act: -0.1700
Data Index: 8279532 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2546. Min Act: -0.1700
Data Index: 3668670 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2859. Min Act: -0.1700
Data Index: 3336916 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2859. Min Act: -0.1700
Data Index: 7069512 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2859. Min Act: -0.1700
Data Index: 5142732 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2859. Min Act: -0.1700
Data Index: 3802819 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2859. Min Act: -0.1700
Data Index: 510252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2859. Min Act: -0.1700
Data Index: 3695226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.1921. Min Act: -0.1700
Data Index: 8764803 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2234. Min Act: -0.1700
Data Index: 996900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2234. Min Act: -0.1700
Data Index: 2626196 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2234. Min Act: -0.1700
Data Index: 1122663 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.2234. Min Act: -0.1700
Data Index: 8587499 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.1608. Min Act: -0.1700
Data Index: 7565644 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.1921. Min Act: -0.1700
Data Index: 2959108 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3484. Min Range: -4.3484
Max Act: 4.1921. Min Act: -0.1700
Data Index: 8392944 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19