Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 395 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0353. Min Act: -0.1700
Data Index: 3092106 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0353. Min Act: -0.1700
Data Index: 8741534 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0353. Min Act: -0.1700
Data Index: 8063468 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0041. Min Act: -0.1700
Data Index: 6552909 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9728. Min Act: -0.1700
Data Index: 3526123 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9728. Min Act: -0.1700
Data Index: 4134267 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9728. Min Act: -0.1700
Data Index: 275043 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9416. Min Act: -0.1700
Data Index: 1684194 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9416. Min Act: -0.1700
Data Index: 1226278 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9416. Min Act: -0.1700
Data Index: 5506117 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9416. Min Act: -0.1700
Data Index: 1683491 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 1614010 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 2975680 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 3652064 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 4922419 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8791. Min Act: -0.1700
Data Index: 2921995 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7853. Min Act: -0.1700
Data Index: 3023641 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8166. Min Act: -0.1700
Data Index: 381522 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7853. Min Act: -0.1700
Data Index: 2742728 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8166. Min Act: -0.1700
Data Index: 7065355 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19