Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0678. Min Range: -8.0678
Max Act: 8.0678. Min Act: -0.1700
Data Index: 4473830 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0678. Min Range: -8.0678
Max Act: 8.0053. Min Act: -0.1700
Data Index: 1032665 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.9428. Min Act: -0.1700
Data Index: 4382652 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0678. Min Range: -8.0678
Max Act: 8.0053. Min Act: -0.1700
Data Index: 8256968 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.9428. Min Act: -0.1700
Data Index: 8291409 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.8803. Min Act: -0.1700
Data Index: 8810586 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.7553. Min Act: -0.1700
Data Index: 1356340 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.8178. Min Act: -0.1700
Data Index: 1996953 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.8178. Min Act: -0.1700
Data Index: 1225984 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.8178. Min Act: -0.1700
Data Index: 8747535 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.7553. Min Act: -0.1700
Data Index: 972516 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.7553. Min Act: -0.1700
Data Index: 4130364 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.8178. Min Act: -0.1700
Data Index: 1307219 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.7553. Min Act: -0.1700
Data Index: 1246286 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.7553. Min Act: -0.1700
Data Index: 673499 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.7553. Min Act: -0.1700
Data Index: 7267632 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.7553. Min Act: -0.1700
Data Index: 6382987 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.8178. Min Act: -0.1700
Data Index: 421415 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.7553. Min Act: -0.1700
Data Index: 3518890 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0678. Min Range: -8.0678
Max Act: 7.6928. Min Act: -0.1700
Data Index: 4795729 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19