Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2420 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.5124. Min Act: -0.1700
Data Index: 5600068 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.3874. Min Act: -0.1700
Data Index: 6586108 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2624. Min Act: -0.1700
Data Index: 5957746 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2312. Min Act: -0.1700
Data Index: 1243311 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1999. Min Act: -0.1700
Data Index: 6221494 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.2312. Min Act: -0.1700
Data Index: 2825133 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1999. Min Act: -0.1700
Data Index: 4548563 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1686. Min Act: -0.1700
Data Index: 5763625 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1686. Min Act: -0.1700
Data Index: 1677335 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1686. Min Act: -0.1700
Data Index: 6593009 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1061. Min Act: -0.1700
Data Index: 6255826 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1061. Min Act: -0.1700
Data Index: 1609908 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1374. Min Act: -0.1700
Data Index: 6228636 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1374. Min Act: -0.1700
Data Index: 5986752 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1374. Min Act: -0.1700
Data Index: 3868881 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1061. Min Act: -0.1700
Data Index: 3756681 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1061. Min Act: -0.1700
Data Index: 5409100 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1061. Min Act: -0.1700
Data Index: 1025860 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1061. Min Act: -0.1700
Data Index: 2430480 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5124. Min Range: -4.5124
Max Act: 4.1061. Min Act: -0.1700
Data Index: 1677339 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19