Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.2749. Min Act: -0.1700
Data Index: 8817858 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2749. Min Range: -6.2749
Max Act: 6.0874. Min Act: -0.1700
Data Index: 991678 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.9937. Min Act: -0.1700
Data Index: 908033 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.9624. Min Act: -0.1700
Data Index: 3348781 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.8999. Min Act: -0.1700
Data Index: 885824 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.8374. Min Act: -0.1700
Data Index: 7476697 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.8062. Min Act: -0.1700
Data Index: 5678266 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.7124. Min Act: -0.1700
Data Index: 845195 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.7124. Min Act: -0.1698
Data Index: 3241492 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.7124. Min Act: -0.1700
Data Index: 8148697 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.7124. Min Act: -0.1700
Data Index: 1167974 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.7124. Min Act: -0.1700
Data Index: 8258653 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.6812. Min Act: -0.1700
Data Index: 8817865 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.6812. Min Act: -0.1698
Data Index: 2539901 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.6499. Min Act: -0.1700
Data Index: 4826242 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.6499. Min Act: -0.1700
Data Index: 5321244 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.6499. Min Act: -0.1700
Data Index: 5321245 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.6187. Min Act: -0.1698
Data Index: 1806670 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.6187. Min Act: -0.1700
Data Index: 7050070 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2749. Min Range: -6.2749
Max Act: 5.5874. Min Act: -0.1675
Data Index: 7476690 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19