Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2374 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.2527. Min Act: -0.1700
Data Index: 6604584 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.2215. Min Act: -0.1700
Data Index: 4009059 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.2215. Min Act: -0.1700
Data Index: 3577089 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.1902. Min Act: -0.1700
Data Index: 2454174 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.1277. Min Act: -0.1700
Data Index: 1372282 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.0652. Min Act: -0.1700
Data Index: 3284734 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.0652. Min Act: -0.1700
Data Index: 4155588 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.0340. Min Act: -0.1700
Data Index: 5856577 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.0340. Min Act: -0.1700
Data Index: 223057 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2527. Min Range: -6.2527
Max Act: 6.0340. Min Act: -0.1700
Data Index: 7240028 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9715. Min Act: -0.1700
Data Index: 6499899 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9715. Min Act: -0.1700
Data Index: 2253880 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9402. Min Act: -0.1700
Data Index: 3061113 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9402. Min Act: -0.1700
Data Index: 1589194 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9402. Min Act: -0.1700
Data Index: 3357569 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9402. Min Act: -0.1700
Data Index: 4452830 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9402. Min Act: -0.1700
Data Index: 8705023 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.9090. Min Act: -0.1700
Data Index: 2681205 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.8777. Min Act: -0.1700
Data Index: 5145256 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2527. Min Range: -6.2527
Max Act: 5.8777. Min Act: -0.1700
Data Index: 6092505 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19