Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 946 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.4678. Min Act: -0.1700
Data Index: 8413949 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.4365. Min Act: -0.1700
Data Index: 8435174 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.4053. Min Act: -0.1700
Data Index: 3131495 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.4053. Min Act: -0.1700
Data Index: 7305079 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.3428. Min Act: -0.1700
Data Index: 2362269 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.3428. Min Act: -0.1700
Data Index: 6066708 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.3115. Min Act: -0.1700
Data Index: 4698510 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.3115. Min Act: -0.1700
Data Index: 4802966 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.3115. Min Act: -0.1700
Data Index: 3972646 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.3115. Min Act: -0.1700
Data Index: 6209380 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2803. Min Act: -0.1700
Data Index: 421945 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2490. Min Act: -0.1700
Data Index: 1755603 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2803. Min Act: -0.1700
Data Index: 651517 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2803. Min Act: -0.1700
Data Index: 8826893 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2803. Min Act: -0.1700
Data Index: 8553444 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2490. Min Act: -0.1700
Data Index: 1658263 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2803. Min Act: -0.1700
Data Index: 5549588 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2490. Min Act: -0.1700
Data Index: 214360 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2490. Min Act: -0.1700
Data Index: 7114797 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4678. Min Range: -5.4678
Max Act: 5.2490. Min Act: -0.1700
Data Index: 806971 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19