Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2759 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.9674. Min Act: -0.1700
Data Index: 1156123 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.8111. Min Act: -0.1700
Data Index: 4250851 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.8424. Min Act: -0.1700
Data Index: 6474394 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.8111. Min Act: -0.1700
Data Index: 3806918 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.7174. Min Act: -0.1700
Data Index: 8580967 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.6549. Min Act: -0.1700
Data Index: 3946468 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5924. Min Act: -0.1700
Data Index: 5158242 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5924. Min Act: -0.1700
Data Index: 6167782 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5924. Min Act: -0.1700
Data Index: 5142243 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5924. Min Act: -0.1700
Data Index: 4430358 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5611. Min Act: -0.1700
Data Index: 2345512 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5924. Min Act: -0.1700
Data Index: 3238661 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5924. Min Act: -0.1700
Data Index: 4151879 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5611. Min Act: -0.1700
Data Index: 6572554 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5299. Min Act: -0.1700
Data Index: 2429263 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5299. Min Act: -0.1700
Data Index: 118840 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5299. Min Act: -0.1700
Data Index: 1477003 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5299. Min Act: -0.1700
Data Index: 8367878 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5299. Min Act: -0.1700
Data Index: 2774828 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5299. Min Act: -0.1700
Data Index: 3557334 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19