Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0705. Min Range: -4.0705
Max Act: 4.0705. Min Act: -0.1700
Data Index: 7155494 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0705. Min Range: -4.0705
Max Act: 4.0393. Min Act: -0.1700
Data Index: 7857031 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.9455. Min Act: -0.1700
Data Index: 5485046 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.9455. Min Act: -0.1700
Data Index: 8960 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.9455. Min Act: -0.1700
Data Index: 1819178 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.9298. Min Act: -0.1700
Data Index: 4431266 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.8986. Min Act: -0.1700
Data Index: 1860812 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.8360. Min Act: -0.1700
Data Index: 1246453 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.8048. Min Act: -0.1700
Data Index: 4764979 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.8360. Min Act: -0.1700
Data Index: 6110093 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.8048. Min Act: -0.1700
Data Index: 3855164 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.7422. Min Act: -0.1700
Data Index: 6842079 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.7422. Min Act: -0.1700
Data Index: 3020912 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.7422. Min Act: -0.1700
Data Index: 5171667 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.7266. Min Act: -0.1700
Data Index: 4528801 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.7109. Min Act: -0.1700
Data Index: 2113544 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.7109. Min Act: -0.1700
Data Index: 2638286 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.6640. Min Act: -0.1700
Data Index: 1067970 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.6953. Min Act: -0.1700
Data Index: 393212 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0705. Min Range: -4.0705
Max Act: 3.6796. Min Act: -0.1700
Data Index: 1805643 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19