Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2170 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5864. Min Act: -0.1700
Data Index: 7205078 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5864. Min Act: -0.1700
Data Index: 8272900 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5864. Min Act: -0.1700
Data Index: 7799641 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5864. Min Act: -0.1700
Data Index: 4833805 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5551. Min Act: -0.1700
Data Index: 4519627 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5707. Min Act: -0.1700
Data Index: 8151518 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5394. Min Act: -0.1700
Data Index: 7137089 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5394. Min Act: -0.1700
Data Index: 1017616 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5237. Min Act: -0.1700
Data Index: 6491477 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5237. Min Act: -0.1700
Data Index: 6451133 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5237. Min Act: -0.1700
Data Index: 4568438 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.5081. Min Act: -0.1700
Data Index: 2482983 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.4924. Min Act: -0.1700
Data Index: 7774552 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.4924. Min Act: -0.1700
Data Index: 4835716 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.4768. Min Act: -0.1700
Data Index: 1598147 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.4924. Min Act: -0.1700
Data Index: 6578294 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.4768. Min Act: -0.1700
Data Index: 1756913 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.4768. Min Act: -0.1700
Data Index: 2367990 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.4768. Min Act: -0.1700
Data Index: 4237525 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5864. Min Range: -3.5864
Max Act: 3.4924. Min Act: -0.1700
Data Index: 895420 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19