Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 627 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.8637. Min Act: -0.1700
Data Index: 7214012 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.6135. Min Act: -0.1700
Data Index: 7503172 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.5822. Min Act: -0.1700
Data Index: 8744863 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.5509. Min Act: -0.1700
Data Index: 1286047 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.5509. Min Act: -0.1700
Data Index: 1654953 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.5196. Min Act: -0.1700
Data Index: 3873754 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.5196. Min Act: -0.1700
Data Index: 1186403 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4882. Min Act: -0.1700
Data Index: 4787954 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.5039. Min Act: -0.1700
Data Index: 5927901 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4726. Min Act: -0.1700
Data Index: 7886771 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4726. Min Act: -0.1700
Data Index: 2900730 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4726. Min Act: -0.1700
Data Index: 935949 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4726. Min Act: -0.1700
Data Index: 7051143 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4726. Min Act: -0.1700
Data Index: 161061 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4726. Min Act: -0.1700
Data Index: 2892997 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4569. Min Act: -0.1700
Data Index: 4881690 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4569. Min Act: -0.1700
Data Index: 1127103 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4256. Min Act: -0.1700
Data Index: 7930864 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4412. Min Act: -0.1700
Data Index: 3585556 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8637. Min Range: -3.8637
Max Act: 3.4412. Min Act: -0.1700
Data Index: 7655825 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19