Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.9100. Min Act: -0.1700
Data Index: 5157781 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.7850. Min Act: -0.1700
Data Index: 3856900 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6600. Min Act: -0.1700
Data Index: 6858056 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6600. Min Act: -0.1700
Data Index: 4637613 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.6287. Min Act: -0.1700
Data Index: 4904438 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5975. Min Act: -0.1700
Data Index: 963323 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5975. Min Act: -0.1700
Data Index: 700382 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5662. Min Act: -0.1700
Data Index: 5374833 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5037. Min Act: -0.1700
Data Index: 4978077 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5037. Min Act: -0.1700
Data Index: 1927405 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5037. Min Act: -0.1700
Data Index: 3996293 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5037. Min Act: -0.1700
Data Index: 975501 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5037. Min Act: -0.1700
Data Index: 4736018 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.4412. Min Act: -0.1700
Data Index: 7016551 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.4725. Min Act: -0.1700
Data Index: 285551 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.4725. Min Act: -0.1700
Data Index: 2174491 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.4412. Min Act: -0.1700
Data Index: 264588 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.4412. Min Act: -0.1700
Data Index: 5067574 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.4412. Min Act: -0.1700
Data Index: 4259871 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.4412. Min Act: -0.1700
Data Index: 80047 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19