Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2370 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.6479. Min Act: -0.1700
Data Index: 1399245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5853. Min Act: -0.1700
Data Index: 4977578 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5853. Min Act: -0.1700
Data Index: 447071 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5540. Min Act: -0.1700
Data Index: 5243227 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5540. Min Act: -0.1700
Data Index: 1077577 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.4913. Min Act: -0.1700
Data Index: 2240951 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 2728704 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 6040609 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 6177010 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 6270440 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 6336667 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.4913. Min Act: -0.1700
Data Index: 3644485 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 7456188 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 8126876 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 8510636 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 4930372 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 5811272 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.5226. Min Act: -0.1700
Data Index: 5258939 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.4913. Min Act: -0.1700
Data Index: 4436484 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6479. Min Range: -3.6479
Max Act: 3.4913. Min Act: -0.1700
Data Index: 4970756 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19