Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1215 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.7289. Min Act: -0.1700
Data Index: 6431535 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.7129. Min Act: -0.1700
Data Index: 7126894 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6969. Min Act: -0.1700
Data Index: 4156041 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6648. Min Act: -0.1700
Data Index: 2894196 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6809. Min Act: -0.1700
Data Index: 2894193 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6327. Min Act: -0.1700
Data Index: 3409436 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6327. Min Act: -0.1700
Data Index: 2894195 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6327. Min Act: -0.1700
Data Index: 3527836 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6167. Min Act: -0.1700
Data Index: 6448641 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.5845. Min Act: -0.1700
Data Index: 668512 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6006. Min Act: -0.1700
Data Index: 4123276 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6006. Min Act: -0.1700
Data Index: 5049976 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.5684. Min Act: -0.1700
Data Index: 147835 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.5845. Min Act: -0.1700
Data Index: 8748803 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.5845. Min Act: -0.1700
Data Index: 2112695 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.5845. Min Act: -0.1700
Data Index: 511617 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.5684. Min Act: -0.1700
Data Index: 599630 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.5845. Min Act: -0.1700
Data Index: 8717480 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.6006. Min Act: -0.1700
Data Index: 383581 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7289. Min Range: -2.7289
Max Act: 2.5684. Min Act: -0.1700
Data Index: 2660568 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19