Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.9033. Min Act: -0.1700
Data Index: 7334149 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.8096. Min Act: -0.1700
Data Index: 149226 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.8096. Min Act: -0.1700
Data Index: 716932 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.7783. Min Act: -0.1700
Data Index: 278825 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.6846. Min Act: -0.1700
Data Index: 3707767 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.6533. Min Act: -0.1700
Data Index: 5271680 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.6221. Min Act: -0.1700
Data Index: 3564948 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.5283. Min Act: -0.1700
Data Index: 5543717 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.4971. Min Act: -0.1700
Data Index: 278828 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.4658. Min Act: -0.1700
Data Index: 2580534 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.4658. Min Act: -0.1700
Data Index: 184139 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.3721. Min Act: -0.1700
Data Index: 4534968 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.3408. Min Act: -0.1700
Data Index: 3910117 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.3721. Min Act: -0.1700
Data Index: 6400912 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.3096. Min Act: -0.1700
Data Index: 4357501 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.3096. Min Act: -0.1700
Data Index: 5739746 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.3096. Min Act: -0.1700
Data Index: 2332120 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.3096. Min Act: -0.1700
Data Index: 6162395 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.2471. Min Act: -0.1700
Data Index: 2226179 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.2783. Min Act: -0.1700
Data Index: 3895756 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19