Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4246 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.8534. Min Act: -0.1700
Data Index: 2559448 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.8221. Min Act: -0.1700
Data Index: 2968295 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.7909. Min Act: -0.1700
Data Index: 5328574 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.7909. Min Act: -0.1700
Data Index: 6849815 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.7596. Min Act: -0.1700
Data Index: 8711281 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.7284. Min Act: -0.1700
Data Index: 4631129 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.7284. Min Act: -0.1700
Data Index: 3451424 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6659. Min Act: -0.1700
Data Index: 1959229 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6659. Min Act: -0.1700
Data Index: 4555997 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6346. Min Act: -0.1700
Data Index: 8139176 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6346. Min Act: -0.1700
Data Index: 5801046 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6346. Min Act: -0.1700
Data Index: 6837834 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6346. Min Act: -0.1700
Data Index: 4279636 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.5721. Min Act: -0.1700
Data Index: 7565512 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6034. Min Act: -0.1700
Data Index: 752661 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6034. Min Act: -0.1700
Data Index: 4556009 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.5721. Min Act: -0.1700
Data Index: 407717 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6034. Min Act: -0.1700
Data Index: 1966587 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.6034. Min Act: -0.1700
Data Index: 2386506 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8534. Min Range: -4.8534
Max Act: 4.5721. Min Act: -0.1700
Data Index: 6376962 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19