Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.2504. Min Act: -0.1700
Data Index: 2730792 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.2347. Min Act: -0.1700
Data Index: 5248388 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.1561. Min Act: -0.1700
Data Index: 7307199 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.1088. Min Act: -0.1700
Data Index: 5954026 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0931. Min Act: -0.1700
Data Index: 7224017 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0773. Min Act: -0.1700
Data Index: 3960815 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0931. Min Act: -0.1700
Data Index: 1420679 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0931. Min Act: -0.1700
Data Index: 4149049 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0773. Min Act: -0.1700
Data Index: 1833932 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0773. Min Act: -0.1700
Data Index: 4724359 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0615. Min Act: -0.1700
Data Index: 709565 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0773. Min Act: -0.1700
Data Index: 1845171 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0615. Min Act: -0.1700
Data Index: 3977728 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0615. Min Act: -0.1700
Data Index: 2035638 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0615. Min Act: -0.1700
Data Index: 6002945 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0773. Min Act: -0.1700
Data Index: 6967950 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0773. Min Act: -0.1700
Data Index: 1916702 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0458. Min Act: -0.1700
Data Index: 2035640 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0615. Min Act: -0.1700
Data Index: 4409886 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2504. Min Range: -3.2504
Max Act: 3.0458. Min Act: -0.1700
Data Index: 5109191 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19