Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2055. Min Range: -6.2055
Max Act: 6.2055. Min Act: -0.1700
Data Index: 4252662 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2055. Min Range: -6.2055
Max Act: 6.1742. Min Act: -0.1700
Data Index: 2542748 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2055. Min Range: -6.2055
Max Act: 6.2055. Min Act: -0.1700
Data Index: 7828361 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2055. Min Range: -6.2055
Max Act: 6.1117. Min Act: -0.1700
Data Index: 7333785 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2055. Min Range: -6.2055
Max Act: 6.1117. Min Act: -0.1700
Data Index: 2104203 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2055. Min Range: -6.2055
Max Act: 6.0492. Min Act: -0.1700
Data Index: 4720465 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2055. Min Range: -6.2055
Max Act: 6.0180. Min Act: -0.1700
Data Index: 5907908 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.9867. Min Act: -0.1700
Data Index: 1379687 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.9555. Min Act: -0.1700
Data Index: 4691374 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.9867. Min Act: -0.1700
Data Index: 3010418 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.9867. Min Act: -0.1700
Data Index: 1055787 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.9867. Min Act: -0.1700
Data Index: 2387043 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.9242. Min Act: -0.1700
Data Index: 1881609 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.8930. Min Act: -0.1700
Data Index: 8436321 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.8930. Min Act: -0.1700
Data Index: 3610337 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.8617. Min Act: -0.1700
Data Index: 8008789 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.8930. Min Act: -0.1700
Data Index: 3597856 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.8930. Min Act: -0.1700
Data Index: 1563997 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.8617. Min Act: -0.1700
Data Index: 3642892 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2055. Min Range: -6.2055
Max Act: 5.8617. Min Act: -0.1700
Data Index: 2371083 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19