Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.4187. Min Act: -0.1700
Data Index: 8095057 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3717. Min Act: -0.1700
Data Index: 720276 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3717. Min Act: -0.1700
Data Index: 6251813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3717. Min Act: -0.1700
Data Index: 8156647 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3560. Min Act: -0.1700
Data Index: 4730415 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3560. Min Act: -0.1700
Data Index: 6144041 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 4321424 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 8040506 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 7399088 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 2328423 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 773012 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 3751642 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 2313703 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3246. Min Act: -0.1700
Data Index: 220344 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3246. Min Act: -0.1700
Data Index: 59475 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 3415930 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3246. Min Act: -0.1700
Data Index: 6769017 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 3222900 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3246. Min Act: -0.1700
Data Index: 793656 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4187. Min Range: -3.4187
Max Act: 3.3403. Min Act: -0.1700
Data Index: 5783790 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19