Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2101 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.4551. Min Act: -0.1700
Data Index: 1684110 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.4551. Min Act: -0.1700
Data Index: 192694 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.4238. Min Act: -0.1700
Data Index: 5066070 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.4238. Min Act: -0.1700
Data Index: 5168260 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.3926. Min Act: -0.1700
Data Index: 5663095 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.3926. Min Act: -0.1700
Data Index: 836561 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.3613. Min Act: -0.1700
Data Index: 3860174 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.3613. Min Act: -0.1700
Data Index: 2302530 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.3613. Min Act: -0.1700
Data Index: 7043237 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.2676. Min Act: -0.1700
Data Index: 1442048 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.2676. Min Act: -0.1700
Data Index: 6146679 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.2676. Min Act: -0.1700
Data Index: 6897587 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.2363. Min Act: -0.1700
Data Index: 556889 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.2363. Min Act: -0.1700
Data Index: 1061655 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.2363. Min Act: -0.1700
Data Index: 730164 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.2051. Min Act: -0.1700
Data Index: 5551928 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.2051. Min Act: -0.1700
Data Index: 1169497 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.2051. Min Act: -0.1700
Data Index: 2340139 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.1738. Min Act: -0.1700
Data Index: 3177668 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4551. Min Range: -7.4551
Max Act: 7.1738. Min Act: -0.1700
Data Index: 6444283 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19