Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 843 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.8638. Min Act: -0.1700
Data Index: 7477915 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.6138. Min Act: -0.1700
Data Index: 1064952 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.5825. Min Act: -0.1700
Data Index: 7442681 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 2985431 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 4411728 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 2669403 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4263. Min Act: -0.1700
Data Index: 6730490 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.4263. Min Act: -0.1700
Data Index: 8344870 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3950. Min Act: -0.1700
Data Index: 866093 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3950. Min Act: -0.1700
Data Index: 2542953 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3950. Min Act: -0.1700
Data Index: 7397364 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3325. Min Act: -0.1700
Data Index: 2157385 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3325. Min Act: -0.1700
Data Index: 8001095 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3013. Min Act: -0.1700
Data Index: 4614982 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3013. Min Act: -0.1700
Data Index: 1795998 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3013. Min Act: -0.1700
Data Index: 580641 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.3013. Min Act: -0.1700
Data Index: 6815695 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.2700. Min Act: -0.1700
Data Index: 4668474 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.2700. Min Act: -0.1700
Data Index: 2452855 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8638. Min Range: -6.8638
Max Act: 6.2700. Min Act: -0.1700
Data Index: 8685131 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19