Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0590. Min Range: -3.0590
Max Act: 3.0590. Min Act: -0.1700
Data Index: 2832112 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0590. Min Range: -3.0590
Max Act: 3.0116. Min Act: -0.1700
Data Index: 8565634 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.9325. Min Act: -0.1700
Data Index: 373309 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.9325. Min Act: -0.1700
Data Index: 843927 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.9167. Min Act: -0.1700
Data Index: 205691 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.9167. Min Act: -0.1700
Data Index: 7120056 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.9008. Min Act: -0.1700
Data Index: 5303138 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.9008. Min Act: -0.1700
Data Index: 4772416 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.9008. Min Act: -0.1700
Data Index: 3995203 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8849. Min Act: -0.1700
Data Index: 7792355 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.9008. Min Act: -0.1700
Data Index: 8580412 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8373. Min Act: -0.1700
Data Index: 8068203 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8214. Min Act: -0.1700
Data Index: 5648755 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8373. Min Act: -0.1700
Data Index: 4928222 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8214. Min Act: -0.1700
Data Index: 5810704 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8691. Min Act: -0.1700
Data Index: 7052204 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8691. Min Act: -0.1700
Data Index: 6915083 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8373. Min Act: -0.1700
Data Index: 5091992 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8055. Min Act: -0.1700
Data Index: 825334 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0590. Min Range: -3.0590
Max Act: 2.8055. Min Act: -0.1700
Data Index: 1148308 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19