Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.8774. Min Act: -0.1700
Data Index: 1283566 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.8462. Min Act: -0.1700
Data Index: 4067306 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.8149. Min Act: -0.1700
Data Index: 8344278 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.7212. Min Act: -0.1700
Data Index: 114541 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.6587. Min Act: -0.1700
Data Index: 3551985 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.6274. Min Act: -0.1700
Data Index: 2847204 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.6274. Min Act: -0.1700
Data Index: 2955874 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.6274. Min Act: -0.1700
Data Index: 5983868 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.5962. Min Act: -0.1700
Data Index: 3688740 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.5649. Min Act: -0.1700
Data Index: 3165600 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.5024. Min Act: -0.1700
Data Index: 8121010 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.5337. Min Act: -0.1700
Data Index: 6410836 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.5337. Min Act: -0.1700
Data Index: 4239797 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.5337. Min Act: -0.1700
Data Index: 4199218 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.5649. Min Act: -0.1700
Data Index: 4117439 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.4712. Min Act: -0.1700
Data Index: 2050555 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.4712. Min Act: -0.1700
Data Index: 3589679 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.4399. Min Act: -0.1700
Data Index: 1229409 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.4399. Min Act: -0.1700
Data Index: 8277300 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8774. Min Range: -6.8774
Max Act: 6.4399. Min Act: -0.1700
Data Index: 1146717 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19