Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.3684. Min Act: -0.1700
Data Index: 6764822 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.1809. Min Act: -0.1700
Data Index: 3113080 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.1809. Min Act: -0.1700
Data Index: 2336005 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.2121. Min Act: -0.1700
Data Index: 3675679 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.1496. Min Act: -0.1700
Data Index: 7262556 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.1184. Min Act: -0.1700
Data Index: 2506500 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0871. Min Act: -0.1700
Data Index: 1317202 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0559. Min Act: -0.1700
Data Index: 8704280 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0871. Min Act: -0.1700
Data Index: 6137714 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0559. Min Act: -0.1700
Data Index: 7985615 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0246. Min Act: -0.1700
Data Index: 4122700 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0559. Min Act: -0.1700
Data Index: 7386177 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0559. Min Act: -0.1700
Data Index: 6827702 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0559. Min Act: -0.1700
Data Index: 1666501 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0559. Min Act: -0.1700
Data Index: 1990643 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0246. Min Act: -0.1700
Data Index: 3743621 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0246. Min Act: -0.1700
Data Index: 1726460 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0246. Min Act: -0.1700
Data Index: 4645220 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3684. Min Range: -7.3684
Max Act: 7.0559. Min Act: -0.1700
Data Index: 2697942 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3684. Min Range: -7.3684
Max Act: 6.9934. Min Act: -0.1700
Data Index: 7389298 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19