Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.5550. Min Act: -0.1700
Data Index: 7383068 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.3988. Min Act: -0.1700
Data Index: 4014553 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.4613. Min Act: -0.1700
Data Index: 6231242 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.3363. Min Act: -0.1700
Data Index: 1613388 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.3363. Min Act: -0.1700
Data Index: 5191967 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.3050. Min Act: -0.1700
Data Index: 5875683 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.2738. Min Act: -0.1700
Data Index: 1002097 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.2738. Min Act: -0.1700
Data Index: 1420747 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.2738. Min Act: -0.1700
Data Index: 2993650 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.3050. Min Act: -0.1700
Data Index: 5087718 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.2425. Min Act: -0.1700
Data Index: 4360438 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.2425. Min Act: -0.1700
Data Index: 3836552 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.2113. Min Act: -0.1700
Data Index: 413519 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.1800. Min Act: -0.1700
Data Index: 4223054 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.1800. Min Act: -0.1700
Data Index: 2263988 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.1800. Min Act: -0.1699
Data Index: 1060670 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.1800. Min Act: -0.1700
Data Index: 3361555 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.1800. Min Act: -0.1700
Data Index: 6142300 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.1488. Min Act: -0.1700
Data Index: 3155724 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5550. Min Range: -6.5550
Max Act: 6.1488. Min Act: -0.1700
Data Index: 5714955 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19