Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2215 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.9497. Min Act: -0.1700
Data Index: 2684177 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.8559. Min Act: -0.1700
Data Index: 8474371 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.8247. Min Act: -0.1700
Data Index: 4886010 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.8247. Min Act: -0.1700
Data Index: 3842398 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.7934. Min Act: -0.1700
Data Index: 4765929 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.7622. Min Act: -0.1700
Data Index: 682500 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.7622. Min Act: -0.1700
Data Index: 5275364 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.7309. Min Act: -0.1700
Data Index: 6375741 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.7309. Min Act: -0.1700
Data Index: 5255203 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6997. Min Act: -0.1700
Data Index: 6820966 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6997. Min Act: -0.1700
Data Index: 884284 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6997. Min Act: -0.1700
Data Index: 2080766 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6997. Min Act: -0.1700
Data Index: 4402292 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6684. Min Act: -0.1700
Data Index: 3127576 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6684. Min Act: -0.1700
Data Index: 742804 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6997. Min Act: -0.1700
Data Index: 7627145 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6684. Min Act: -0.1700
Data Index: 2355864 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6684. Min Act: -0.1700
Data Index: 5580391 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6372. Min Act: -0.1700
Data Index: 5625937 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9497. Min Range: -4.9497
Max Act: 4.6372. Min Act: -0.1700
Data Index: 2520660 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19