Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3754 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2130. Min Range: -5.2130
Max Act: 5.2130. Min Act: -0.1700
Data Index: 6020213 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2130. Min Range: -5.2130
Max Act: 5.1817. Min Act: -0.1700
Data Index: 4399553 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.9942. Min Act: -0.1700
Data Index: 2356089 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2130. Min Range: -5.2130
Max Act: 5.0255. Min Act: -0.1700
Data Index: 2478995 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.9942. Min Act: -0.1700
Data Index: 1484289 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.9630. Min Act: -0.1700
Data Index: 5144526 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.9630. Min Act: -0.1700
Data Index: 6285740 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.9630. Min Act: -0.1700
Data Index: 8516174 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.9317. Min Act: -0.1700
Data Index: 3758814 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.9005. Min Act: -0.1700
Data Index: 8344064 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.8692. Min Act: -0.1700
Data Index: 7363202 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.9005. Min Act: -0.1700
Data Index: 7184227 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.8380. Min Act: -0.1700
Data Index: 7716787 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.8380. Min Act: -0.1700
Data Index: 2363777 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.8067. Min Act: -0.1700
Data Index: 2935995 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.8067. Min Act: -0.1700
Data Index: 3961825 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.8067. Min Act: -0.1700
Data Index: 2853606 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.8067. Min Act: -0.1700
Data Index: 1198893 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.7755. Min Act: -0.1700
Data Index: 4908390 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2130. Min Range: -5.2130
Max Act: 4.8067. Min Act: -0.1700
Data Index: 7319006 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19