Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5826 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.9469. Min Act: -0.1700
Data Index: 6929771 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.8844. Min Act: -0.1700
Data Index: 1061563 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.7907. Min Act: -0.1700
Data Index: 1961991 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.6969. Min Act: -0.1700
Data Index: 421741 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.6969. Min Act: -0.1700
Data Index: 7153905 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.6657. Min Act: -0.1700
Data Index: 6003894 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.6032. Min Act: -0.1700
Data Index: 7545945 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.6032. Min Act: -0.1700
Data Index: 1336054 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.5719. Min Act: -0.1700
Data Index: 6103079 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.5094. Min Act: -0.1700
Data Index: 3889575 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.4782. Min Act: -0.1700
Data Index: 7239062 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.5094. Min Act: -0.1700
Data Index: 7604627 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.4782. Min Act: -0.1700
Data Index: 4099925 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.4469. Min Act: -0.1700
Data Index: 654873 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.4157. Min Act: -0.1700
Data Index: 4069163 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.4157. Min Act: -0.1700
Data Index: 1470803 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.4157. Min Act: -0.1700
Data Index: 3669794 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.3844. Min Act: -0.1700
Data Index: 2392816 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.3844. Min Act: -0.1700
Data Index: 91401 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.3532. Min Act: -0.1700
Data Index: 7278047 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19