Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0286. Min Range: -2.0286
Max Act: 2.0286. Min Act: -0.1700
Data Index: 2103791 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0286. Min Range: -2.0286
Max Act: 2.0117. Min Act: -0.1700
Data Index: 4683010 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9948. Min Act: -0.1700
Data Index: 3464312 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9948. Min Act: -0.1700
Data Index: 7664708 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9948. Min Act: -0.1700
Data Index: 3220029 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9779. Min Act: -0.1700
Data Index: 8225759 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9948. Min Act: -0.1700
Data Index: 344274 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9948. Min Act: -0.1700
Data Index: 2320413 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9779. Min Act: -0.1700
Data Index: 6714123 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9948. Min Act: -0.1700
Data Index: 5987345 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9779. Min Act: -0.1700
Data Index: 2336715 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9610. Min Act: -0.1700
Data Index: 2870753 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9610. Min Act: -0.1700
Data Index: 3889293 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9440. Min Act: -0.1700
Data Index: 5943917 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9440. Min Act: -0.1700
Data Index: 843279 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9610. Min Act: -0.1700
Data Index: 2423733 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9610. Min Act: -0.1700
Data Index: 76264 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9610. Min Act: -0.1700
Data Index: 114922 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9610. Min Act: -0.1700
Data Index: 182255 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0286. Min Range: -2.0286
Max Act: 1.9610. Min Act: -0.1700
Data Index: 2269115 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19