Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.3471. Min Act: -0.1700
Data Index: 7735496 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.2846. Min Act: -0.1700
Data Index: 1058216 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.1284. Min Act: -0.1700
Data Index: 7044287 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.0659. Min Act: -0.1700
Data Index: 6078955 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.0033. Min Act: -0.1700
Data Index: 636541 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.0346. Min Act: -0.1700
Data Index: 528592 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.0346. Min Act: -0.1700
Data Index: 8187237 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.0033. Min Act: -0.1700
Data Index: 4045801 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.0033. Min Act: -0.1700
Data Index: 713363 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3471. Min Range: -4.3471
Max Act: 3.9721. Min Act: -0.1700
Data Index: 5681525 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.0346. Min Act: -0.1700
Data Index: 5596687 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3471. Min Range: -4.3471
Max Act: 3.9721. Min Act: -0.1700
Data Index: 2658204 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3471. Min Range: -4.3471
Max Act: 4.0033. Min Act: -0.1700
Data Index: 4839427 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3471. Min Range: -4.3471
Max Act: 3.9408. Min Act: -0.1700
Data Index: 8101346 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3471. Min Range: -4.3471
Max Act: 3.9408. Min Act: -0.1700
Data Index: 4849401 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3471. Min Range: -4.3471
Max Act: 3.9408. Min Act: -0.1700
Data Index: 6214292 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3471. Min Range: -4.3471
Max Act: 3.9408. Min Act: -0.1700
Data Index: 6406441 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3471. Min Range: -4.3471
Max Act: 3.9408. Min Act: -0.1700
Data Index: 3086402 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3471. Min Range: -4.3471
Max Act: 3.9096. Min Act: -0.1700
Data Index: 5099572 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3471. Min Range: -4.3471
Max Act: 3.9721. Min Act: -0.1700
Data Index: 851897 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19