Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.8918. Min Act: -0.1700
Data Index: 4745104 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.7980. Min Act: -0.1700
Data Index: 2266986 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.5480. Min Act: -0.1700
Data Index: 2360070 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.5480. Min Act: -0.1700
Data Index: 1345412 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.4855. Min Act: -0.1700
Data Index: 7819369 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.4855. Min Act: -0.1700
Data Index: 2697571 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.4855. Min Act: -0.1700
Data Index: 5422586 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.4543. Min Act: -0.1700
Data Index: 6715324 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.4855. Min Act: -0.1700
Data Index: 4402548 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.4543. Min Act: -0.1700
Data Index: 5429997 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.4230. Min Act: -0.1700
Data Index: 7070379 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.3918. Min Act: -0.1700
Data Index: 8794817 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.3918. Min Act: -0.1700
Data Index: 104141 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.3605. Min Act: -0.1700
Data Index: 6111288 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.3605. Min Act: -0.1700
Data Index: 6426647 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.3605. Min Act: -0.1700
Data Index: 6329968 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.3293. Min Act: -0.1700
Data Index: 1984967 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.3293. Min Act: -0.1700
Data Index: 5828826 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.2980. Min Act: -0.1700
Data Index: 8040946 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8918. Min Range: -5.8918
Max Act: 5.2980. Min Act: -0.1700
Data Index: 2831723 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19