Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2032 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.7987. Min Act: -0.1700
Data Index: 231096 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.7675. Min Act: -0.1700
Data Index: 5541489 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.7362. Min Act: -0.1700
Data Index: 2928896 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.5487. Min Act: -0.1700
Data Index: 1468469 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.4862. Min Act: -0.1700
Data Index: 8708560 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.2987. Min Act: -0.1700
Data Index: 8599125 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.2675. Min Act: -0.1700
Data Index: 2160688 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.2987. Min Act: -0.1700
Data Index: 2922581 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.2362. Min Act: -0.1700
Data Index: 3193848 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.1737. Min Act: -0.1700
Data Index: 935439 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.1737. Min Act: -0.1700
Data Index: 7362087 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.1737. Min Act: -0.1700
Data Index: 4712837 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.1112. Min Act: -0.1700
Data Index: 6399526 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.1112. Min Act: -0.1700
Data Index: 3084334 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.1425. Min Act: -0.1700
Data Index: 5625659 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.1112. Min Act: -0.1700
Data Index: 2687967 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.1112. Min Act: -0.1700
Data Index: 2278844 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.0800. Min Act: -0.1700
Data Index: 5310867 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.0800. Min Act: -0.1700
Data Index: 1712640 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7987. Min Range: -5.7987
Max Act: 5.0487. Min Act: -0.1700
Data Index: 8675431 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19