Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5219 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1836. Min Range: -6.1836
Max Act: 6.1836. Min Act: -0.1700
Data Index: 1084745 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.9336. Min Act: -0.1700
Data Index: 6599559 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.8399. Min Act: -0.1700
Data Index: 2197633 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.7774. Min Act: -0.1700
Data Index: 633160 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.7774. Min Act: -0.1700
Data Index: 2236957 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.7461. Min Act: -0.1700
Data Index: 4490552 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.7461. Min Act: -0.1700
Data Index: 5966906 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.7461. Min Act: -0.1700
Data Index: 5020583 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.7461. Min Act: -0.1700
Data Index: 1935144 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.7149. Min Act: -0.1700
Data Index: 5447764 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6211. Min Act: -0.1700
Data Index: 3700862 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6211. Min Act: -0.1700
Data Index: 8656539 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6524. Min Act: -0.1700
Data Index: 8289060 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6524. Min Act: -0.1700
Data Index: 7558732 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6524. Min Act: -0.1700
Data Index: 6173248 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6524. Min Act: -0.1700
Data Index: 1114421 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6836. Min Act: -0.1700
Data Index: 5083709 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6524. Min Act: -0.1700
Data Index: 8764593 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6211. Min Act: -0.1700
Data Index: 788657 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1836. Min Range: -6.1836
Max Act: 5.6211. Min Act: -0.1700
Data Index: 413068 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19