Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6198 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.7618. Min Act: -0.1700
Data Index: 8005133 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.7306. Min Act: -0.1700
Data Index: 922808 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.5743. Min Act: -0.1700
Data Index: 3065069 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.2931. Min Act: -0.1700
Data Index: 5099051 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.2931. Min Act: -0.1700
Data Index: 4855127 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.2931. Min Act: -0.1700
Data Index: 7351186 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.2931. Min Act: -0.1700
Data Index: 8302435 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.2618. Min Act: -0.1700
Data Index: 1739442 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.2618. Min Act: -0.1700
Data Index: 2004531 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.2618. Min Act: -0.1700
Data Index: 4837986 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1993. Min Act: -0.1700
Data Index: 4346905 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1993. Min Act: -0.1700
Data Index: 3497202 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1993. Min Act: -0.1700
Data Index: 1382453 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1681. Min Act: -0.1700
Data Index: 1356677 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1681. Min Act: -0.1700
Data Index: 676076 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1368. Min Act: -0.1700
Data Index: 3509216 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1368. Min Act: -0.1700
Data Index: 6258122 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1681. Min Act: -0.1700
Data Index: 2902625 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1368. Min Act: -0.1700
Data Index: 2942053 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7618. Min Range: -6.7618
Max Act: 6.1368. Min Act: -0.1700
Data Index: 8260204 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19