Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6645. Min Range: -9.6645
Max Act: 9.6645. Min Act: -0.1700
Data Index: 7025343 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6645. Min Range: -9.6645
Max Act: 9.4770. Min Act: -0.1700
Data Index: 29074 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6645. Min Range: -9.6645
Max Act: 9.2895. Min Act: -0.1700
Data Index: 1654708 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6645. Min Range: -9.6645
Max Act: 9.2270. Min Act: -0.1700
Data Index: 7764386 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6645. Min Range: -9.6645
Max Act: 9.1645. Min Act: -0.1700
Data Index: 1821847 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6645. Min Range: -9.6645
Max Act: 9.2270. Min Act: -0.1700
Data Index: 1208321 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6645. Min Range: -9.6645
Max Act: 9.0395. Min Act: -0.1700
Data Index: 1870387 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.9145. Min Act: -0.1700
Data Index: 4585362 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.8520. Min Act: -0.1700
Data Index: 2280160 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.8520. Min Act: -0.1700
Data Index: 5409017 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.8520. Min Act: -0.1700
Data Index: 7089706 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.7270. Min Act: -0.1700
Data Index: 1141055 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.7270. Min Act: -0.1700
Data Index: 4499907 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.6645. Min Act: -0.1700
Data Index: 1445087 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.6645. Min Act: -0.1700
Data Index: 1229640 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.7270. Min Act: -0.1700
Data Index: 6106410 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.6645. Min Act: -0.1700
Data Index: 8685590 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.7270. Min Act: -0.1700
Data Index: 4929417 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.6645. Min Act: -0.1700
Data Index: 5467233 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6645. Min Range: -9.6645
Max Act: 8.6020. Min Act: -0.1700
Data Index: 1886048 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19