Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.8510. Min Act: -0.1700
Data Index: 4410191 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.6947. Min Act: -0.1700
Data Index: 6171174 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.6635. Min Act: -0.1700
Data Index: 784722 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.6322. Min Act: -0.1700
Data Index: 8473103 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.6322. Min Act: -0.1700
Data Index: 2999747 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.5697. Min Act: -0.1700
Data Index: 1814153 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.5385. Min Act: -0.1700
Data Index: 548745 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.5072. Min Act: -0.1700
Data Index: 4801997 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.5385. Min Act: -0.1700
Data Index: 3752204 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.4760. Min Act: -0.1700
Data Index: 4693774 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.4760. Min Act: -0.1700
Data Index: 5048171 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.4760. Min Act: -0.1700
Data Index: 6168026 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.4135. Min Act: -0.1700
Data Index: 2911555 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.4135. Min Act: -0.1700
Data Index: 6925289 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.3822. Min Act: -0.1700
Data Index: 7095372 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.4135. Min Act: -0.1700
Data Index: 1505111 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.3822. Min Act: -0.1700
Data Index: 1053725 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.3510. Min Act: -0.1700
Data Index: 1910990 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.3510. Min Act: -0.1700
Data Index: 710781 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8510. Min Range: -6.8510
Max Act: 6.3510. Min Act: -0.1700
Data Index: 7204730 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19