Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1029 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0553. Min Range: -3.0553
Max Act: 3.0553. Min Act: -0.1700
Data Index: 7294651 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0553. Min Range: -3.0553
Max Act: 3.0237. Min Act: -0.1700
Data Index: 204368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0553. Min Range: -3.0553
Max Act: 3.0237. Min Act: -0.1700
Data Index: 4400544 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0553. Min Range: -3.0553
Max Act: 3.0079. Min Act: -0.1700
Data Index: 4279630 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0553. Min Range: -3.0553
Max Act: 3.0079. Min Act: -0.1700
Data Index: 2048216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0553. Min Range: -3.0553
Max Act: 3.0079. Min Act: -0.1700
Data Index: 3545277 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0553. Min Range: -3.0553
Max Act: 3.0079. Min Act: -0.1700
Data Index: 7197202 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9921. Min Act: -0.1700
Data Index: 3867901 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9921. Min Act: -0.1700
Data Index: 8685256 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9763. Min Act: -0.1700
Data Index: 4105099 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9921. Min Act: -0.1700
Data Index: 4416961 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9763. Min Act: -0.1700
Data Index: 8729729 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9605. Min Act: -0.1700
Data Index: 7899252 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9605. Min Act: -0.1700
Data Index: 4174185 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9763. Min Act: -0.1700
Data Index: 1365725 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9605. Min Act: -0.1700
Data Index: 5516367 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9605. Min Act: -0.1700
Data Index: 1072326 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9605. Min Act: -0.1700
Data Index: 8571964 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9763. Min Act: -0.1700
Data Index: 1160106 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0553. Min Range: -3.0553
Max Act: 2.9605. Min Act: -0.1700
Data Index: 8720524 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19