Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7164. Min Range: -9.7164
Max Act: 9.7164. Min Act: -0.1700
Data Index: 98932 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7164. Min Range: -9.7164
Max Act: 9.2789. Min Act: -0.1700
Data Index: 1953694 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7164. Min Range: -9.7164
Max Act: 9.1539. Min Act: -0.1700
Data Index: 5786340 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7164. Min Range: -9.7164
Max Act: 9.1539. Min Act: -0.1700
Data Index: 544243 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7164. Min Range: -9.7164
Max Act: 9.0289. Min Act: -0.1700
Data Index: 705030 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.9664. Min Act: -0.1700
Data Index: 6881706 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.9664. Min Act: -0.1700
Data Index: 6281178 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.9664. Min Act: -0.1700
Data Index: 1525147 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.9664. Min Act: -0.1700
Data Index: 6559574 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.9039. Min Act: -0.1700
Data Index: 6092358 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.9039. Min Act: -0.1700
Data Index: 6953799 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.9039. Min Act: -0.1700
Data Index: 7604828 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.8414. Min Act: -0.1700
Data Index: 7833022 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.8414. Min Act: -0.1700
Data Index: 4369683 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.8414. Min Act: -0.1700
Data Index: 6865011 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.8414. Min Act: -0.1700
Data Index: 2152872 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.8414. Min Act: -0.1700
Data Index: 7636955 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.7789. Min Act: -0.1700
Data Index: 7015185 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.7164. Min Act: -0.1700
Data Index: 3494735 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7164. Min Range: -9.7164
Max Act: 8.6539. Min Act: -0.1700
Data Index: 4841601 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19