Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.3905. Min Act: -0.1700
Data Index: 4394201 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.2655. Min Act: -0.1700
Data Index: 3185881 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1717. Min Act: -0.1700
Data Index: 4304725 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1717. Min Act: -0.1700
Data Index: 7274893 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1717. Min Act: -0.1700
Data Index: 6338919 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1717. Min Act: -0.1700
Data Index: 1547881 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1405. Min Act: -0.1700
Data Index: 7913760 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1092. Min Act: -0.1700
Data Index: 467175 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1092. Min Act: -0.1700
Data Index: 1671412 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.1092. Min Act: -0.1700
Data Index: 8274817 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0780. Min Act: -0.1700
Data Index: 309730 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0780. Min Act: -0.1700
Data Index: 8271435 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0467. Min Act: -0.1700
Data Index: 1459584 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0155. Min Act: -0.1700
Data Index: 8431169 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0155. Min Act: -0.1700
Data Index: 2056622 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0155. Min Act: -0.1700
Data Index: 392364 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3905. Min Range: -5.3905
Max Act: 4.9842. Min Act: -0.1700
Data Index: 7075481 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3905. Min Range: -5.3905
Max Act: 4.9842. Min Act: -0.1700
Data Index: 2666680 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3905. Min Range: -5.3905
Max Act: 4.9842. Min Act: -0.1700
Data Index: 2627454 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3905. Min Range: -5.3905
Max Act: 5.0155. Min Act: -0.1700
Data Index: 2164069 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19