Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1737. Min Range: -4.1737
Max Act: 4.1737. Min Act: -0.1700
Data Index: 1162050 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1737. Min Range: -4.1737
Max Act: 4.0799. Min Act: -0.1700
Data Index: 6964750 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1737. Min Range: -4.1737
Max Act: 4.0487. Min Act: -0.1700
Data Index: 2358718 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1737. Min Range: -4.1737
Max Act: 4.0174. Min Act: -0.1700
Data Index: 5431952 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1737. Min Range: -4.1737
Max Act: 4.0174. Min Act: -0.1700
Data Index: 8368032 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9862. Min Act: -0.1700
Data Index: 5478853 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1737. Min Range: -4.1737
Max Act: 4.0174. Min Act: -0.1700
Data Index: 3650200 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9549. Min Act: -0.1700
Data Index: 60649 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9549. Min Act: -0.1700
Data Index: 3835204 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9549. Min Act: -0.1700
Data Index: 6042521 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9549. Min Act: -0.1700
Data Index: 4837661 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9549. Min Act: -0.1700
Data Index: 2085516 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9549. Min Act: -0.1700
Data Index: 2765657 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9236. Min Act: -0.1700
Data Index: 3384962 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9236. Min Act: -0.1700
Data Index: 5844128 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.8924. Min Act: -0.1700
Data Index: 6634697 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9236. Min Act: -0.1700
Data Index: 5000127 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.9236. Min Act: -0.1700
Data Index: 2085515 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.8924. Min Act: -0.1700
Data Index: 8777514 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1737. Min Range: -4.1737
Max Act: 3.8924. Min Act: -0.1700
Data Index: 2570189 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19