Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1922 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2579. Min Range: -7.2579
Max Act: 7.2579. Min Act: -0.1700
Data Index: 1265618 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2579. Min Range: -7.2579
Max Act: 7.2266. Min Act: -0.1700
Data Index: 8049820 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2579. Min Range: -7.2579
Max Act: 7.0391. Min Act: -0.1700
Data Index: 8805211 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2579. Min Range: -7.2579
Max Act: 7.0704. Min Act: -0.1700
Data Index: 2158996 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2579. Min Range: -7.2579
Max Act: 7.0704. Min Act: -0.1700
Data Index: 243722 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2579. Min Range: -7.2579
Max Act: 7.0704. Min Act: -0.1700
Data Index: 3848550 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2579. Min Range: -7.2579
Max Act: 7.0391. Min Act: -0.1700
Data Index: 327036 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2579. Min Range: -7.2579
Max Act: 7.0391. Min Act: -0.1700
Data Index: 869737 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9766. Min Act: -0.1700
Data Index: 922264 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9766. Min Act: -0.1700
Data Index: 2794271 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9766. Min Act: -0.1700
Data Index: 6145151 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2579. Min Range: -7.2579
Max Act: 7.0079. Min Act: -0.1700
Data Index: 5287679 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9766. Min Act: -0.1700
Data Index: 4199416 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9454. Min Act: -0.1700
Data Index: 7791571 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9766. Min Act: -0.1700
Data Index: 4691979 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9454. Min Act: -0.1700
Data Index: 133235 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9454. Min Act: -0.1700
Data Index: 1041525 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9454. Min Act: -0.1700
Data Index: 4163909 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9141. Min Act: -0.1700
Data Index: 1170952 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2579. Min Range: -7.2579
Max Act: 6.9141. Min Act: -0.1700
Data Index: 1885696 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19