Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4133 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.8672. Min Act: -0.1700
Data Index: 1908496 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 6225690 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 6516744 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.7422. Min Act: -0.1700
Data Index: 6888432 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 1309032 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.6172. Min Act: -0.1700
Data Index: 7689026 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.6797. Min Act: -0.1700
Data Index: 663287 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.6172. Min Act: -0.1700
Data Index: 7767589 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.6172. Min Act: -0.1700
Data Index: 8001756 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.6172. Min Act: -0.1700
Data Index: 6118383 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 6813016 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 6535221 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.4297. Min Act: -0.1700
Data Index: 5089124 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 4196475 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 3825809 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 3482499 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.5547. Min Act: -0.1700
Data Index: 6494562 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 2911082 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.4297. Min Act: -0.1700
Data Index: 6449706 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8672. Min Range: -8.8672
Max Act: 8.4922. Min Act: -0.1700
Data Index: 683412 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19