Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5275 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2283. Min Range: -8.2283
Max Act: 8.2283. Min Act: -0.1700
Data Index: 8504539 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2283. Min Range: -8.2283
Max Act: 8.1658. Min Act: -0.1700
Data Index: 3404336 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2283. Min Range: -8.2283
Max Act: 8.1658. Min Act: -0.1700
Data Index: 5837795 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2283. Min Range: -8.2283
Max Act: 8.1033. Min Act: -0.1700
Data Index: 4967458 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.9470. Min Act: -0.1700
Data Index: 2314926 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.9470. Min Act: -0.1700
Data Index: 7190222 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.9783. Min Act: -0.1700
Data Index: 2622678 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.9158. Min Act: -0.1700
Data Index: 4104803 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.9158. Min Act: -0.1700
Data Index: 4980966 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8845. Min Act: -0.1700
Data Index: 4925800 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8845. Min Act: -0.1700
Data Index: 339870 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8845. Min Act: -0.1700
Data Index: 2565992 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8533. Min Act: -0.1700
Data Index: 5565525 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8533. Min Act: -0.1700
Data Index: 3781350 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8220. Min Act: -0.1700
Data Index: 6642949 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8220. Min Act: -0.1700
Data Index: 1876833 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8220. Min Act: -0.1700
Data Index: 5108427 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8220. Min Act: -0.1700
Data Index: 2339322 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.8220. Min Act: -0.1700
Data Index: 453750 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2283. Min Range: -8.2283
Max Act: 7.7595. Min Act: -0.1700
Data Index: 4925801 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19