Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4719 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.9630. Min Act: -0.1700
Data Index: 801805 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.9005. Min Act: -0.1700
Data Index: 3324387 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.7755. Min Act: -0.1700
Data Index: 1115630 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.7755. Min Act: -0.1700
Data Index: 6099219 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.7130. Min Act: -0.1700
Data Index: 2698163 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.6505. Min Act: -0.1700
Data Index: 7055911 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.6505. Min Act: -0.1700
Data Index: 1658203 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.6505. Min Act: -0.1700
Data Index: 6555299 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.5880. Min Act: -0.1700
Data Index: 6364128 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.5880. Min Act: -0.1700
Data Index: 2070137 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.5880. Min Act: -0.1700
Data Index: 893608 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.5255. Min Act: -0.1700
Data Index: 4484688 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.5255. Min Act: -0.1700
Data Index: 2569998 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.4630. Min Act: -0.1700
Data Index: 7745652 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.4630. Min Act: -0.1700
Data Index: 6827430 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.5255. Min Act: -0.1700
Data Index: 4432730 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.4630. Min Act: -0.1700
Data Index: 7517522 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.4630. Min Act: -0.1700
Data Index: 1507939 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.4630. Min Act: -0.1700
Data Index: 6701304 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9630. Min Range: -7.9630
Max Act: 7.4630. Min Act: -0.1700
Data Index: 4422674 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19