Model: None
Dataset: The Pile
Neuron 3310 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.0096. Min Range: -3.0096
Max Act: 3.0096. Min Act: -0.1700
Data Index: 1209328 (The Pile)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9938. Min Act: -0.1700
Data Index: 3003144 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9938. Min Act: -0.1700
Data Index: 1498337 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9938. Min Act: -0.1700
Data Index: 4878264 (The Pile)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9938. Min Act: -0.1700
Data Index: 8848105 (The Pile)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9938. Min Act: -0.1700
Data Index: 2669790 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9938. Min Act: -0.1700
Data Index: 1817594 (The Pile)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9780. Min Act: -0.1700
Data Index: 5238603 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9780. Min Act: -0.1700
Data Index: 9080245 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9622. Min Act: -0.1700
Data Index: 775729 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9622. Min Act: -0.1700
Data Index: 10077892 (The Pile)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9622. Min Act: -0.1700
Data Index: 3469526 (The Pile)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9464. Min Act: -0.1700
Data Index: 1541751 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9305. Min Act: -0.1700
Data Index: 7824256 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9305. Min Act: -0.1700
Data Index: 683540 (The Pile)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9147. Min Act: -0.1700
Data Index: 8570761 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9147. Min Act: -0.1700
Data Index: 9696176 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9147. Min Act: -0.1700
Data Index: 404065 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.9147. Min Act: -0.1700
Data Index: 1648166 (The Pile)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0096. Min Range: -3.0096
Max Act: 2.8988. Min Act: -0.1700
Data Index: 7377734 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19