Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4831 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2882. Min Range: -5.2882
Max Act: 5.2882. Min Act: -0.1700
Data Index: 1772347 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2882. Min Range: -5.2882
Max Act: 5.2257. Min Act: -0.1700
Data Index: 8600101 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2882. Min Range: -5.2882
Max Act: 5.1944. Min Act: -0.1700
Data Index: 1990595 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2882. Min Range: -5.2882
Max Act: 5.1319. Min Act: -0.1700
Data Index: 8185709 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2882. Min Range: -5.2882
Max Act: 5.1007. Min Act: -0.1700
Data Index: 7177487 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.9132. Min Act: -0.1700
Data Index: 2911638 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.9757. Min Act: -0.1700
Data Index: 7037688 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.9444. Min Act: -0.1700
Data Index: 6146670 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.9132. Min Act: -0.1700
Data Index: 8263032 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.9132. Min Act: -0.1700
Data Index: 5097499 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.9444. Min Act: -0.1700
Data Index: 6242678 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.9132. Min Act: -0.1700
Data Index: 1963955 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.8819. Min Act: -0.1700
Data Index: 888574 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.9132. Min Act: -0.1700
Data Index: 1899621 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.8819. Min Act: -0.1700
Data Index: 2494456 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.8507. Min Act: -0.1700
Data Index: 6426301 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.8507. Min Act: -0.1700
Data Index: 6405094 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.8507. Min Act: -0.1700
Data Index: 8247261 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.8507. Min Act: -0.1700
Data Index: 4137137 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2882. Min Range: -5.2882
Max Act: 4.8507. Min Act: -0.1700
Data Index: 2192665 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19