Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2635. Min Range: -7.2635
Max Act: 7.2635. Min Act: -0.1700
Data Index: 6990979 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2635. Min Range: -7.2635
Max Act: 7.1698. Min Act: -0.1700
Data Index: 1820163 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2635. Min Range: -7.2635
Max Act: 7.0760. Min Act: -0.1700
Data Index: 5204914 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2635. Min Range: -7.2635
Max Act: 7.0760. Min Act: -0.1700
Data Index: 4710586 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2635. Min Range: -7.2635
Max Act: 7.1073. Min Act: -0.1700
Data Index: 34655 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.9510. Min Act: -0.1700
Data Index: 2266906 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.9198. Min Act: -0.1700
Data Index: 865973 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.9198. Min Act: -0.1700
Data Index: 6275463 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.8573. Min Act: -0.1700
Data Index: 1617134 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.8260. Min Act: -0.1700
Data Index: 4606518 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.8260. Min Act: -0.1700
Data Index: 2106163 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.8260. Min Act: -0.1700
Data Index: 5286072 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.7948. Min Act: -0.1700
Data Index: 7078927 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.8260. Min Act: -0.1700
Data Index: 5565498 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.7948. Min Act: -0.1700
Data Index: 2700360 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.7635. Min Act: -0.1700
Data Index: 2621753 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.7948. Min Act: -0.1700
Data Index: 782779 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.7323. Min Act: -0.1700
Data Index: 3671568 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.6698. Min Act: -0.1700
Data Index: 5024360 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2635. Min Range: -7.2635
Max Act: 6.6698. Min Act: -0.1700
Data Index: 3719888 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19