Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2951 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.8954. Min Act: -0.1700
Data Index: 1227442 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.5829. Min Act: -0.1700
Data Index: 8535930 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.3954. Min Act: -0.1700
Data Index: 5170837 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.3329. Min Act: -0.1700
Data Index: 7264525 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2079. Min Act: -0.1700
Data Index: 5070102 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2704. Min Act: -0.1700
Data Index: 671961 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2079. Min Act: -0.1700
Data Index: 376260 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2079. Min Act: -0.1700
Data Index: 4280224 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2079. Min Act: -0.1700
Data Index: 5497501 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2079. Min Act: -0.1700
Data Index: 4790295 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2079. Min Act: -0.1700
Data Index: 4567109 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2079. Min Act: -0.1700
Data Index: 38497 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2079. Min Act: -0.1700
Data Index: 4310304 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.2079. Min Act: -0.1700
Data Index: 8331463 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.1454. Min Act: -0.1700
Data Index: 688948 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.0829. Min Act: -0.1700
Data Index: 577687 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.0204. Min Act: -0.1700
Data Index: 5402284 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.0204. Min Act: -0.1700
Data Index: 7969826 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.0204. Min Act: -0.1700
Data Index: 7994496 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8954. Min Range: -9.8954
Max Act: 9.0204. Min Act: -0.1700
Data Index: 2537948 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19