Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5320 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.7693. Min Act: -0.1700
Data Index: 5465457 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.3006. Min Act: -0.1700
Data Index: 6915896 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.2068. Min Act: -0.1700
Data Index: 397596 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.1756. Min Act: -0.1700
Data Index: 7427818 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.1756. Min Act: -0.1700
Data Index: 3366293 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.1131. Min Act: -0.1700
Data Index: 6452727 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.1131. Min Act: -0.1700
Data Index: 3850107 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.1131. Min Act: -0.1700
Data Index: 8107405 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0818. Min Act: -0.1700
Data Index: 3252931 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0818. Min Act: -0.1700
Data Index: 3255818 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.1131. Min Act: -0.1700
Data Index: 8545827 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0818. Min Act: -0.1700
Data Index: 4665040 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0506. Min Act: -0.1700
Data Index: 72916 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0506. Min Act: -0.1700
Data Index: 1122970 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0193. Min Act: -0.1700
Data Index: 3850116 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0193. Min Act: -0.1700
Data Index: 1788169 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0193. Min Act: -0.1700
Data Index: 7279716 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7693. Min Range: -7.7693
Max Act: 6.9881. Min Act: -0.1700
Data Index: 1711752 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7693. Min Range: -7.7693
Max Act: 7.0193. Min Act: -0.1700
Data Index: 1790995 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7693. Min Range: -7.7693
Max Act: 6.9568. Min Act: -0.1700
Data Index: 4888800 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19