Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2393 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.6996. Min Act: -0.1700
Data Index: 5838418 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.6684. Min Act: -0.1700
Data Index: 5984114 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.6059. Min Act: -0.1700
Data Index: 2457614 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.5121. Min Act: -0.1700
Data Index: 5314323 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.5121. Min Act: -0.1700
Data Index: 4025674 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.5121. Min Act: -0.1700
Data Index: 4265113 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.4809. Min Act: -0.1700
Data Index: 3365520 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.4809. Min Act: -0.1700
Data Index: 1139187 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.4496. Min Act: -0.1700
Data Index: 1888954 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.4496. Min Act: -0.1700
Data Index: 2898366 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.4183. Min Act: -0.1700
Data Index: 5271570 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.4183. Min Act: -0.1700
Data Index: 7767111 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.3871. Min Act: -0.1700
Data Index: 307831 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.3558. Min Act: -0.1700
Data Index: 1093057 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.3558. Min Act: -0.1700
Data Index: 617943 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.3246. Min Act: -0.1700
Data Index: 420017 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.2933. Min Act: -0.1700
Data Index: 4052263 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.3246. Min Act: -0.1700
Data Index: 5777664 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.3558. Min Act: -0.1700
Data Index: 6371322 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6996. Min Range: -4.6996
Max Act: 4.2933. Min Act: -0.1700
Data Index: 1934077 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19