Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1352 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0982. Min Range: -6.0982
Max Act: 6.0982. Min Act: -0.1700
Data Index: 4738465 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0982. Min Range: -6.0982
Max Act: 6.0357. Min Act: -0.1700
Data Index: 3327715 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0982. Min Range: -6.0982
Max Act: 6.0044. Min Act: -0.1700
Data Index: 5462618 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0982. Min Range: -6.0982
Max Act: 6.0044. Min Act: -0.1700
Data Index: 3478558 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.9419. Min Act: -0.1700
Data Index: 19210 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.9107. Min Act: -0.1700
Data Index: 8168586 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.9419. Min Act: -0.1700
Data Index: 2303319 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.9419. Min Act: -0.1700
Data Index: 2807277 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.8794. Min Act: -0.1700
Data Index: 3366952 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.9107. Min Act: -0.1700
Data Index: 2154279 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.8482. Min Act: -0.1700
Data Index: 52263 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.8482. Min Act: -0.1700
Data Index: 3043545 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.8169. Min Act: -0.1700
Data Index: 3628844 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.8169. Min Act: -0.1700
Data Index: 5511311 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.8169. Min Act: -0.1700
Data Index: 1838785 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.7544. Min Act: -0.1700
Data Index: 3962622 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.7857. Min Act: -0.1700
Data Index: 8551151 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.7544. Min Act: -0.1700
Data Index: 7855638 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.6919. Min Act: -0.1700
Data Index: 592666 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0982. Min Range: -6.0982
Max Act: 5.7232. Min Act: -0.1700
Data Index: 2352820 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19