Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5800 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4394. Min Range: -6.4394
Max Act: 6.4394. Min Act: -0.1700
Data Index: 4475205 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4394. Min Range: -6.4394
Max Act: 6.3144. Min Act: -0.1700
Data Index: 552312 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4394. Min Range: -6.4394
Max Act: 6.2519. Min Act: -0.1700
Data Index: 5153310 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4394. Min Range: -6.4394
Max Act: 6.2207. Min Act: -0.1700
Data Index: 1417156 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4394. Min Range: -6.4394
Max Act: 6.1894. Min Act: -0.1700
Data Index: 7923357 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4394. Min Range: -6.4394
Max Act: 6.1269. Min Act: -0.1700
Data Index: 5083176 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4394. Min Range: -6.4394
Max Act: 6.0957. Min Act: -0.1700
Data Index: 1449199 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.9707. Min Act: -0.1700
Data Index: 3108887 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.9707. Min Act: -0.1700
Data Index: 4781675 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4394. Min Range: -6.4394
Max Act: 6.0019. Min Act: -0.1700
Data Index: 1941245 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.9394. Min Act: -0.1700
Data Index: 3528444 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.9082. Min Act: -0.1700
Data Index: 8374510 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.8457. Min Act: -0.1700
Data Index: 2603123 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.8769. Min Act: -0.1700
Data Index: 1165260 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.8769. Min Act: -0.1700
Data Index: 5652606 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.9082. Min Act: -0.1700
Data Index: 7210153 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.8769. Min Act: -0.1700
Data Index: 5760142 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.8769. Min Act: -0.1700
Data Index: 1390669 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.8457. Min Act: -0.1700
Data Index: 3485451 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4394. Min Range: -6.4394
Max Act: 5.8144. Min Act: -0.1700
Data Index: 5754143 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19