Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 240 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.6681. Min Act: -0.1700
Data Index: 4431063 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.2619. Min Act: -0.1700
Data Index: 7648166 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.9806. Min Act: -0.1700
Data Index: 7598008 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6681. Min Range: -6.6681
Max Act: 6.0119. Min Act: -0.1700
Data Index: 1051841 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.9494. Min Act: -0.1700
Data Index: 8498012 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.9181. Min Act: -0.1700
Data Index: 5714264 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.9181. Min Act: -0.1700
Data Index: 792217 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8869. Min Act: -0.1700
Data Index: 3761564 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8869. Min Act: -0.1700
Data Index: 4904420 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8869. Min Act: -0.1700
Data Index: 4709422 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8869. Min Act: -0.1700
Data Index: 2455732 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8869. Min Act: -0.1700
Data Index: 3690294 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8556. Min Act: -0.1700
Data Index: 795310 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8244. Min Act: -0.1700
Data Index: 7983147 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8244. Min Act: -0.1700
Data Index: 1344575 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8244. Min Act: -0.1700
Data Index: 5508696 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.8556. Min Act: -0.1700
Data Index: 448691 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.7931. Min Act: -0.1700
Data Index: 2097729 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.7931. Min Act: -0.1700
Data Index: 5435231 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6681. Min Range: -6.6681
Max Act: 5.7931. Min Act: -0.1700
Data Index: 7093617 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19