Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1192 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.4493. Min Act: -0.1700
Data Index: 2537029 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.3677. Min Act: -0.1700
Data Index: 7513377 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.3349. Min Act: -0.1700
Data Index: 3147579 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2856. Min Act: -0.1700
Data Index: 3878460 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2856. Min Act: -0.1700
Data Index: 1252859 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2692. Min Act: -0.1700
Data Index: 2198860 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2692. Min Act: -0.1700
Data Index: 5941563 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2526. Min Act: -0.1700
Data Index: 8463047 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2361. Min Act: -0.1700
Data Index: 4118645 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2361. Min Act: -0.1700
Data Index: 973142 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2361. Min Act: -0.1700
Data Index: 8572803 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2196. Min Act: -0.1700
Data Index: 5524601 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2196. Min Act: -0.1700
Data Index: 1975529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2196. Min Act: -0.1700
Data Index: 1725270 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2196. Min Act: -0.1700
Data Index: 2721135 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2361. Min Act: -0.1700
Data Index: 7593292 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.1864. Min Act: -0.1700
Data Index: 2289095 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2030. Min Act: -0.1700
Data Index: 7739639 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2030. Min Act: -0.1700
Data Index: 6113095 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4493. Min Range: -2.4493
Max Act: 2.2030. Min Act: -0.1700
Data Index: 4526583 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19