Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1260 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2559. Min Range: -7.2559
Max Act: 7.2559. Min Act: -0.1700
Data Index: 5178762 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2559. Min Range: -7.2559
Max Act: 7.2247. Min Act: -0.1700
Data Index: 4314303 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2559. Min Range: -7.2559
Max Act: 7.0684. Min Act: -0.1700
Data Index: 625956 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2559. Min Range: -7.2559
Max Act: 7.0372. Min Act: -0.1700
Data Index: 7562195 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.9747. Min Act: -0.1700
Data Index: 9963 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.9747. Min Act: -0.1700
Data Index: 4454513 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.9434. Min Act: -0.1700
Data Index: 1509601 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.9434. Min Act: -0.1700
Data Index: 880746 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.8809. Min Act: -0.1700
Data Index: 6793061 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.8809. Min Act: -0.1700
Data Index: 3295986 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.9122. Min Act: -0.1700
Data Index: 666254 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.8809. Min Act: -0.1700
Data Index: 1067456 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.8809. Min Act: -0.1700
Data Index: 7742957 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.9122. Min Act: -0.1700
Data Index: 5388120 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.8497. Min Act: -0.1700
Data Index: 6328923 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.8497. Min Act: -0.1700
Data Index: 1395970 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.7872. Min Act: -0.1700
Data Index: 7059664 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.7559. Min Act: -0.1700
Data Index: 1312185 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.8184. Min Act: -0.1700
Data Index: 4367980 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2559. Min Range: -7.2559
Max Act: 6.7872. Min Act: -0.1700
Data Index: 7095388 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19