Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 134 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4016. Min Range: -8.4016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 1636447 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.6828. Min Act: -0.1700
Data Index: 3532670 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.4953. Min Act: -0.1700
Data Index: 7515236 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.4328. Min Act: -0.1700
Data Index: 1636446 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3391. Min Act: -0.1700
Data Index: 4321930 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3391. Min Act: -0.1700
Data Index: 1157752 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3078. Min Act: -0.1700
Data Index: 242714 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.2141. Min Act: -0.1700
Data Index: 2603682 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.2141. Min Act: -0.1700
Data Index: 3791848 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.2141. Min Act: -0.1700
Data Index: 4360491 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.1828. Min Act: -0.1700
Data Index: 3001405 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.0891. Min Act: -0.1700
Data Index: 1961490 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.0891. Min Act: -0.1700
Data Index: 7824778 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.0891. Min Act: -0.1700
Data Index: 2090601 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.0891. Min Act: -0.1700
Data Index: 244688 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.0891. Min Act: -0.1700
Data Index: 179886 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.0891. Min Act: -0.1700
Data Index: 4812289 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.0578. Min Act: -0.1700
Data Index: 8142533 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.0266. Min Act: -0.1700
Data Index: 5253689 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.0266. Min Act: -0.1700
Data Index: 4475644 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19