Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.8533. Min Act: -0.1700
Data Index: 5630145 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.8221. Min Act: -0.1700
Data Index: 4598776 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.8221. Min Act: -0.1700
Data Index: 37703 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.6971. Min Act: -0.1700
Data Index: 6096448 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.5721. Min Act: -0.1700
Data Index: 1011849 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.3533. Min Act: -0.1700
Data Index: 8274696 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.5096. Min Act: -0.1700
Data Index: 2023630 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.5721. Min Act: -0.1700
Data Index: 8736535 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.5096. Min Act: -0.1700
Data Index: 293375 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.3846. Min Act: -0.1700
Data Index: 3860596 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.4158. Min Act: -0.1700
Data Index: 5321698 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.2908. Min Act: -0.1700
Data Index: 4834572 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.2908. Min Act: -0.1700
Data Index: 8467334 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.2596. Min Act: -0.1700
Data Index: 6674651 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.1658. Min Act: -0.1700
Data Index: 4650632 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.1658. Min Act: -0.1700
Data Index: 1201347 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.1346. Min Act: -0.1700
Data Index: 4667399 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.2283. Min Act: -0.1700
Data Index: 4186178 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.1971. Min Act: -0.1700
Data Index: 3023096 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8533. Min Range: -7.8533
Max Act: 7.1346. Min Act: -0.1700
Data Index: 2988129 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19