Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 323 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.6404. Min Act: -0.1700
Data Index: 5008008 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.5778. Min Act: -0.1700
Data Index: 513644 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.5464. Min Act: -0.1700
Data Index: 6044505 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.5778. Min Act: -0.1700
Data Index: 3581305 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4838. Min Act: -0.1700
Data Index: 3175592 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.5151. Min Act: -0.1700
Data Index: 21578 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4838. Min Act: -0.1700
Data Index: 2593743 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4838. Min Act: -0.1700
Data Index: 3444400 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4838. Min Act: -0.1700
Data Index: 6133348 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4525. Min Act: -0.1700
Data Index: 6521629 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4211. Min Act: -0.1700
Data Index: 5698017 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4525. Min Act: -0.1700
Data Index: 270329 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4211. Min Act: -0.1699
Data Index: 1135100 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4838. Min Act: -0.1700
Data Index: 2253672 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4211. Min Act: -0.1700
Data Index: 4599298 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4838. Min Act: -0.1700
Data Index: 4963194 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4838. Min Act: -0.1700
Data Index: 257951 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4525. Min Act: -0.1700
Data Index: 5051605 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4525. Min Act: -0.1700
Data Index: 6759399 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6404. Min Range: -3.6404
Max Act: 3.4211. Min Act: -0.1700
Data Index: 2897282 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19