Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.4048. Min Act: -0.1700
Data Index: 5633882 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.3736. Min Act: -0.1700
Data Index: 7509391 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.3423. Min Act: -0.1700
Data Index: 2984555 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.3111. Min Act: -0.1700
Data Index: 1699800 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.3111. Min Act: -0.1700
Data Index: 4779304 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.3111. Min Act: -0.1700
Data Index: 4810298 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.2798. Min Act: -0.1700
Data Index: 5160268 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.2798. Min Act: -0.1700
Data Index: 1650075 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.2173. Min Act: -0.1700
Data Index: 8330834 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.2173. Min Act: -0.1700
Data Index: 1696100 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1861. Min Act: -0.1700
Data Index: 2468326 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1861. Min Act: -0.1700
Data Index: 8516436 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1861. Min Act: -0.1700
Data Index: 6173718 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1548. Min Act: -0.1700
Data Index: 5783758 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1548. Min Act: -0.1700
Data Index: 7039365 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1548. Min Act: -0.1700
Data Index: 3024251 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1236. Min Act: -0.1700
Data Index: 5561224 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1548. Min Act: -0.1700
Data Index: 654063 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1861. Min Act: -0.1700
Data Index: 6830953 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4048. Min Range: -5.4048
Max Act: 5.1548. Min Act: -0.1700
Data Index: 1375280 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19