Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2649. Min Range: -8.2649
Max Act: 8.2649. Min Act: -0.1700
Data Index: 6602393 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.8587. Min Act: -0.1700
Data Index: 1036084 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.5774. Min Act: -0.1700
Data Index: 1869110 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.6087. Min Act: -0.1700
Data Index: 6122816 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.4524. Min Act: -0.1700
Data Index: 1282681 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.3587. Min Act: -0.1700
Data Index: 57753 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.3274. Min Act: -0.1700
Data Index: 3147009 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.2962. Min Act: -0.1700
Data Index: 2045055 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.2024. Min Act: -0.1700
Data Index: 8455257 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.2024. Min Act: -0.1700
Data Index: 5681233 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.1712. Min Act: -0.1700
Data Index: 4770392 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.1399. Min Act: -0.1700
Data Index: 7041429 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.0774. Min Act: -0.1700
Data Index: 7107656 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.0774. Min Act: -0.1700
Data Index: 2494369 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.0774. Min Act: -0.1700
Data Index: 4806801 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.0774. Min Act: -0.1700
Data Index: 7714055 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.0462. Min Act: -0.1700
Data Index: 21815 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.0462. Min Act: -0.1700
Data Index: 3470054 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2649. Min Range: -8.2649
Max Act: 7.0462. Min Act: -0.1700
Data Index: 1448839 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2649. Min Range: -8.2649
Max Act: 6.9837. Min Act: -0.1700
Data Index: 6550851 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19