Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6341 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2678. Min Range: -6.2678
Max Act: 6.2678. Min Act: -0.1700
Data Index: 6165034 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2678. Min Range: -6.2678
Max Act: 6.2366. Min Act: -0.1700
Data Index: 358078 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2678. Min Range: -6.2678
Max Act: 6.1428. Min Act: -0.1700
Data Index: 4107349 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2678. Min Range: -6.2678
Max Act: 6.1116. Min Act: -0.1700
Data Index: 2054257 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2678. Min Range: -6.2678
Max Act: 6.0178. Min Act: -0.1700
Data Index: 5055163 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2678. Min Range: -6.2678
Max Act: 6.0491. Min Act: -0.1700
Data Index: 3448171 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2678. Min Range: -6.2678
Max Act: 6.0178. Min Act: -0.1700
Data Index: 8014763 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.9866. Min Act: -0.1700
Data Index: 4540387 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.9553. Min Act: -0.1700
Data Index: 5579147 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.9553. Min Act: -0.1700
Data Index: 8727866 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.9241. Min Act: -0.1700
Data Index: 8080648 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.9553. Min Act: -0.1700
Data Index: 3186064 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.8616. Min Act: -0.1700
Data Index: 2423162 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.8616. Min Act: -0.1700
Data Index: 7208657 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.8303. Min Act: -0.1700
Data Index: 827937 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.8303. Min Act: -0.1700
Data Index: 8033357 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.8303. Min Act: -0.1700
Data Index: 305451 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.7991. Min Act: -0.1700
Data Index: 575249 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.7991. Min Act: -0.1700
Data Index: 6677424 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2678. Min Range: -6.2678
Max Act: 5.7991. Min Act: -0.1700
Data Index: 5576439 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19