Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4892 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0857. Min Range: -8.0857
Max Act: 8.0857. Min Act: -0.1700
Data Index: 108788 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.7107. Min Act: -0.1700
Data Index: 246529 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.6482. Min Act: -0.1700
Data Index: 1988616 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.5232. Min Act: -0.1700
Data Index: 687152 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.5232. Min Act: -0.1700
Data Index: 5180079 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.3670. Min Act: -0.1700
Data Index: 7919669 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.3357. Min Act: -0.1700
Data Index: 7091819 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.3357. Min Act: -0.1700
Data Index: 5559105 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.3357. Min Act: -0.1700
Data Index: 4795898 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.3357. Min Act: -0.1700
Data Index: 5520613 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.3045. Min Act: -0.1700
Data Index: 5441456 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.3045. Min Act: -0.1700
Data Index: 7603297 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.3045. Min Act: -0.1700
Data Index: 4975298 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.2420. Min Act: -0.1700
Data Index: 4748437 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.2107. Min Act: -0.1700
Data Index: 3977145 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.1795. Min Act: -0.1700
Data Index: 322033 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.1795. Min Act: -0.1700
Data Index: 5449558 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.2107. Min Act: -0.1700
Data Index: 8443388 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.2107. Min Act: -0.1700
Data Index: 5178129 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.1795. Min Act: -0.1700
Data Index: 4975299 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19