Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 382 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.5346. Min Act: -0.1700
Data Index: 653197 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.4721. Min Act: -0.1700
Data Index: 2512478 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.4408. Min Act: -0.1700
Data Index: 8213962 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.4721. Min Act: -0.1700
Data Index: 3343867 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.4096. Min Act: -0.1700
Data Index: 8493580 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.3471. Min Act: -0.1700
Data Index: 8688785 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.2846. Min Act: -0.1700
Data Index: 7226620 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.2533. Min Act: -0.1700
Data Index: 2636359 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.2533. Min Act: -0.1700
Data Index: 3423337 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.2533. Min Act: -0.1700
Data Index: 247066 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.2846. Min Act: -0.1700
Data Index: 6281214 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.2221. Min Act: -0.1700
Data Index: 1312216 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.2221. Min Act: -0.1700
Data Index: 8469633 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.2533. Min Act: -0.1700
Data Index: 500931 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.1908. Min Act: -0.1700
Data Index: 5029064 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.1596. Min Act: -0.1700
Data Index: 6950216 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.1596. Min Act: -0.1700
Data Index: 3652639 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.1596. Min Act: -0.1700
Data Index: 8118982 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.1596. Min Act: -0.1700
Data Index: 1285564 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5346. Min Range: -5.5346
Max Act: 5.1596. Min Act: -0.1700
Data Index: 7131797 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19