Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5322 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.7087. Min Act: -0.1700
Data Index: 4817389 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.6462. Min Act: -0.1700
Data Index: 4817387 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.5525. Min Act: -0.1700
Data Index: 888366 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.5525. Min Act: -0.1700
Data Index: 7108356 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.5525. Min Act: -0.1700
Data Index: 3306874 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.5525. Min Act: -0.1700
Data Index: 1894709 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.4900. Min Act: -0.1700
Data Index: 2108738 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.5212. Min Act: -0.1700
Data Index: 7131912 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.5212. Min Act: -0.1700
Data Index: 5366894 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.4900. Min Act: -0.1700
Data Index: 5943171 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.4900. Min Act: -0.1700
Data Index: 4817390 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.4587. Min Act: -0.1700
Data Index: 8650556 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.4587. Min Act: -0.1700
Data Index: 7460507 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.4587. Min Act: -0.1700
Data Index: 5672506 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.4587. Min Act: -0.1700
Data Index: 2510492 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.4275. Min Act: -0.1700
Data Index: 6127130 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.4275. Min Act: -0.1700
Data Index: 5512205 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.3962. Min Act: -0.1700
Data Index: 2465325 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.3962. Min Act: -0.1700
Data Index: 7234274 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7087. Min Range: -4.7087
Max Act: 4.3962. Min Act: -0.1700
Data Index: 7705062 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19