Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.8202. Min Act: -0.1700
Data Index: 2037049 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.6327. Min Act: -0.1700
Data Index: 8463832 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.6327. Min Act: -0.1700
Data Index: 2295819 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.5390. Min Act: -0.1700
Data Index: 8355678 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.5077. Min Act: -0.1700
Data Index: 2752363 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.5077. Min Act: -0.1700
Data Index: 7425138 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.5077. Min Act: -0.1700
Data Index: 5612737 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.5077. Min Act: -0.1700
Data Index: 444219 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.5077. Min Act: -0.1700
Data Index: 8567344 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.4765. Min Act: -0.1700
Data Index: 2971496 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.4452. Min Act: -0.1700
Data Index: 1137503 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.4765. Min Act: -0.1700
Data Index: 4108697 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.4452. Min Act: -0.1700
Data Index: 2713141 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.4765. Min Act: -0.1700
Data Index: 2752374 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.4452. Min Act: -0.1700
Data Index: 7866787 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.4140. Min Act: -0.1700
Data Index: 2752375 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.4140. Min Act: -0.1700
Data Index: 1099736 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.3827. Min Act: -0.1700
Data Index: 4923284 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.3827. Min Act: -0.1700
Data Index: 5442177 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8202. Min Range: -6.8202
Max Act: 6.3827. Min Act: -0.1700
Data Index: 4065632 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19