Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6858. Min Range: -5.6858
Max Act: 5.6858. Min Act: -0.1700
Data Index: 4819572 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6858. Min Range: -5.6858
Max Act: 5.5295. Min Act: -0.1700
Data Index: 3474811 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6858. Min Range: -5.6858
Max Act: 5.4983. Min Act: -0.1700
Data Index: 2806875 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6858. Min Range: -5.6858
Max Act: 5.2170. Min Act: -0.1700
Data Index: 2670745 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6858. Min Range: -5.6858
Max Act: 5.2170. Min Act: -0.1700
Data Index: 7916381 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6858. Min Range: -5.6858
Max Act: 5.0608. Min Act: -0.1700
Data Index: 3673152 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6858. Min Range: -5.6858
Max Act: 5.0608. Min Act: -0.1700
Data Index: 5223042 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6858. Min Range: -5.6858
Max Act: 5.0608. Min Act: -0.1700
Data Index: 2566710 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6858. Min Range: -5.6858
Max Act: 5.0295. Min Act: -0.1700
Data Index: 2913742 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.9983. Min Act: -0.1700
Data Index: 5622927 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.9670. Min Act: -0.1700
Data Index: 7638469 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.9358. Min Act: -0.1700
Data Index: 2989684 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.9670. Min Act: -0.1700
Data Index: 5223045 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.9670. Min Act: -0.1700
Data Index: 4300013 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.9358. Min Act: -0.1700
Data Index: 5567745 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.9358. Min Act: -0.1700
Data Index: 2475224 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.9045. Min Act: -0.1700
Data Index: 914413 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.9045. Min Act: -0.1700
Data Index: 2475226 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.8733. Min Act: -0.1700
Data Index: 5710389 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6858. Min Range: -5.6858
Max Act: 4.8733. Min Act: -0.1700
Data Index: 1839613 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19