Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.5590. Min Act: -0.1700
Data Index: 6843018 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.5590. Min Act: -0.1700
Data Index: 8346211 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.5278. Min Act: -0.1700
Data Index: 1093940 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.5278. Min Act: -0.1700
Data Index: 868644 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4965. Min Act: -0.1700
Data Index: 7187523 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4965. Min Act: -0.1700
Data Index: 4420958 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1698
Data Index: 8513746 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4965. Min Act: -0.1700
Data Index: 5476291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1700
Data Index: 1310043 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1700
Data Index: 8700849 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4340. Min Act: -0.1700
Data Index: 6688576 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1700
Data Index: 5991034 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4340. Min Act: -0.1700
Data Index: 5570463 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1700
Data Index: 1144768 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1700
Data Index: 8204027 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1700
Data Index: 7767872 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1700
Data Index: 49065 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1700
Data Index: 7216668 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4653. Min Act: -0.1700
Data Index: 4450143 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5590. Min Range: -4.5590
Max Act: 4.4340. Min Act: -0.1700
Data Index: 2208263 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19