Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.2015. Min Act: -0.1700
Data Index: 3911355 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1516. Min Act: -0.1700
Data Index: 4068887 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1516. Min Act: -0.1700
Data Index: 1743259 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1349. Min Act: -0.1700
Data Index: 2870211 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1349. Min Act: -0.1700
Data Index: 8053396 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1182. Min Act: -0.1700
Data Index: 4522737 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1349. Min Act: -0.1700
Data Index: 5230056 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1182. Min Act: -0.1700
Data Index: 1827160 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1182. Min Act: -0.1700
Data Index: 3768617 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1182. Min Act: -0.1700
Data Index: 701373 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1015. Min Act: -0.1700
Data Index: 597576 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1015. Min Act: -0.1700
Data Index: 1361823 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1015. Min Act: -0.1700
Data Index: 7223825 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1015. Min Act: -0.1700
Data Index: 6823831 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1015. Min Act: -0.1700
Data Index: 1164356 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1182. Min Act: -0.1700
Data Index: 4429719 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.1349. Min Act: -0.1700
Data Index: 958331 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.0679. Min Act: -0.1700
Data Index: 2396481 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.0847. Min Act: -0.1700
Data Index: 5597726 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2015. Min Range: -2.2015
Max Act: 2.0847. Min Act: -0.1700
Data Index: 2494458 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19