Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5580 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.6676. Min Act: -0.1700
Data Index: 5499913 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.5738. Min Act: -0.1700
Data Index: 8197557 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.5426. Min Act: -0.1700
Data Index: 7944696 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4176. Min Act: -0.1700
Data Index: 8197550 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.4176. Min Act: -0.1700
Data Index: 8197556 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.3863. Min Act: -0.1700
Data Index: 1557197 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.3863. Min Act: -0.1700
Data Index: 2822605 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.3551. Min Act: -0.1700
Data Index: 8197551 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.3551. Min Act: -0.1700
Data Index: 5467040 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.2926. Min Act: -0.1700
Data Index: 8197555 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.2613. Min Act: -0.1700
Data Index: 4291197 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.2613. Min Act: -0.1700
Data Index: 7660068 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.2613. Min Act: -0.1700
Data Index: 2308662 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.2301. Min Act: -0.1700
Data Index: 2343659 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.2301. Min Act: -0.1700
Data Index: 6680064 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.2301. Min Act: -0.1700
Data Index: 6956484 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.2301. Min Act: -0.1700
Data Index: 929741 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.1988. Min Act: -0.1700
Data Index: 4376109 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.2301. Min Act: -0.1700
Data Index: 4487018 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6676. Min Range: -5.6676
Max Act: 5.1988. Min Act: -0.1700
Data Index: 3277670 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19