Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4976 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.6990. Min Act: -0.1700
Data Index: 2623822 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.4490. Min Act: -0.1700
Data Index: 1237456 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.3865. Min Act: -0.1700
Data Index: 2962868 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.4177. Min Act: -0.1700
Data Index: 8431361 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.2927. Min Act: -0.1700
Data Index: 6830172 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.2927. Min Act: -0.1700
Data Index: 5447552 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.1990. Min Act: -0.1700
Data Index: 5196922 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.1677. Min Act: -0.1700
Data Index: 891001 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.1052. Min Act: -0.1700
Data Index: 2773400 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0740. Min Act: -0.1700
Data Index: 5872388 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.1052. Min Act: -0.1700
Data Index: 4781108 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0740. Min Act: -0.1700
Data Index: 1794192 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0740. Min Act: -0.1700
Data Index: 4819761 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0427. Min Act: -0.1700
Data Index: 5634007 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0427. Min Act: -0.1700
Data Index: 4323907 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0427. Min Act: -0.1700
Data Index: 6323311 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0740. Min Act: -0.1700
Data Index: 8349423 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0427. Min Act: -0.1700
Data Index: 4415907 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0115. Min Act: -0.1700
Data Index: 1998474 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6990. Min Range: -6.6990
Max Act: 6.0115. Min Act: -0.1700
Data Index: 1101430 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19