Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5533 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.9193. Min Act: -0.1700
Data Index: 3862885 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.7943. Min Act: -0.1700
Data Index: 3470840 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.5443. Min Act: -0.1700
Data Index: 3188699 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.5131. Min Act: -0.1700
Data Index: 5959618 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.4506. Min Act: -0.1700
Data Index: 3672235 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.4506. Min Act: -0.1700
Data Index: 4559062 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.4193. Min Act: -0.1700
Data Index: 7443219 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.4193. Min Act: -0.1700
Data Index: 598145 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.3256. Min Act: -0.1700
Data Index: 1129526 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.2943. Min Act: -0.1700
Data Index: 2656621 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.2631. Min Act: -0.1700
Data Index: 8303976 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.1381. Min Act: -0.1700
Data Index: 464863 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.0756. Min Act: -0.1700
Data Index: 7695106 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.0131. Min Act: -0.1700
Data Index: 5883663 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9193. Min Range: -7.9193
Max Act: 7.0131. Min Act: -0.1700
Data Index: 8663484 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9193. Min Range: -7.9193
Max Act: 6.9818. Min Act: -0.1700
Data Index: 5080039 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9193. Min Range: -7.9193
Max Act: 6.9818. Min Act: -0.1700
Data Index: 3143137 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9193. Min Range: -7.9193
Max Act: 6.9506. Min Act: -0.1700
Data Index: 5220990 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9193. Min Range: -7.9193
Max Act: 6.8881. Min Act: -0.1700
Data Index: 7338523 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9193. Min Range: -7.9193
Max Act: 6.9193. Min Act: -0.1700
Data Index: 7135950 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19