Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5059 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.4658. Min Act: -0.1700
Data Index: 4901787 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.4345. Min Act: -0.1700
Data Index: 1569806 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.3095. Min Act: -0.1696
Data Index: 5193356 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.3095. Min Act: -0.1700
Data Index: 3613395 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.2783. Min Act: -0.1700
Data Index: 4717465 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.1533. Min Act: -0.1700
Data Index: 577235 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.1220. Min Act: -0.1700
Data Index: 3149597 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.1220. Min Act: -0.1700
Data Index: 5290792 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.1220. Min Act: -0.1700
Data Index: 8199219 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0908. Min Act: -0.1700
Data Index: 6844046 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0908. Min Act: -0.1700
Data Index: 7228763 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0595. Min Act: -0.1700
Data Index: 4840681 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0595. Min Act: -0.1700
Data Index: 5427810 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0595. Min Act: -0.1700
Data Index: 2539305 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0595. Min Act: -0.1700
Data Index: 6372241 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0595. Min Act: -0.1700
Data Index: 265605 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0595. Min Act: -0.1700
Data Index: 4448969 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0283. Min Act: -0.1700
Data Index: 2573435 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0283. Min Act: -0.1700
Data Index: 1713962 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4658. Min Range: -5.4658
Max Act: 5.0283. Min Act: -0.1700
Data Index: 1950779 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19