Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5488. Min Range: -6.5488
Max Act: 6.5488. Min Act: -0.1700
Data Index: 6585501 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5488. Min Range: -6.5488
Max Act: 6.3613. Min Act: -0.1700
Data Index: 2224609 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5488. Min Range: -6.5488
Max Act: 6.2988. Min Act: -0.1700
Data Index: 7557724 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5488. Min Range: -6.5488
Max Act: 6.2676. Min Act: -0.1700
Data Index: 8543629 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5488. Min Range: -6.5488
Max Act: 6.2051. Min Act: -0.1700
Data Index: 3164894 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5488. Min Range: -6.5488
Max Act: 6.1113. Min Act: -0.1700
Data Index: 414962 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5488. Min Range: -6.5488
Max Act: 6.1426. Min Act: -0.1700
Data Index: 1417335 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5488. Min Range: -6.5488
Max Act: 6.0488. Min Act: -0.1700
Data Index: 8601941 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5488. Min Range: -6.5488
Max Act: 6.0176. Min Act: -0.1700
Data Index: 1016811 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.9863. Min Act: -0.1700
Data Index: 7393269 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.9863. Min Act: -0.1700
Data Index: 2737997 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.9863. Min Act: -0.1700
Data Index: 7860050 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.9551. Min Act: -0.1700
Data Index: 3198144 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.9551. Min Act: -0.1700
Data Index: 4966615 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.9238. Min Act: -0.1700
Data Index: 1404352 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.8613. Min Act: -0.1700
Data Index: 4452190 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.8926. Min Act: -0.1700
Data Index: 7235208 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.8926. Min Act: -0.1700
Data Index: 546110 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.8926. Min Act: -0.1700
Data Index: 8023676 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5488. Min Range: -6.5488
Max Act: 5.8926. Min Act: -0.1700
Data Index: 7998270 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19