Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1312 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.5300. Min Act: -0.1700
Data Index: 3227454 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.5300. Min Act: -0.1700
Data Index: 6155653 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.4987. Min Act: -0.1700
Data Index: 3749469 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3737. Min Act: -0.1700
Data Index: 4526126 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3737. Min Act: -0.1700
Data Index: 3912581 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3737. Min Act: -0.1700
Data Index: 3749470 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3737. Min Act: -0.1700
Data Index: 4188089 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3737. Min Act: -0.1700
Data Index: 4699020 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3425. Min Act: -0.1700
Data Index: 5607321 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3425. Min Act: -0.1700
Data Index: 3278421 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3425. Min Act: -0.1700
Data Index: 2159547 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3112. Min Act: -0.1700
Data Index: 1310267 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3425. Min Act: -0.1700
Data Index: 792703 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3112. Min Act: -0.1700
Data Index: 4808364 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2800. Min Act: -0.1700
Data Index: 6436488 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2800. Min Act: -0.1700
Data Index: 5863128 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2800. Min Act: -0.1700
Data Index: 6407402 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2175. Min Act: -0.1700
Data Index: 1187038 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2175. Min Act: -0.1700
Data Index: 4140955 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2487. Min Act: -0.1700
Data Index: 3130700 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19