Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1006 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.9469. Min Act: -0.1700
Data Index: 2997801 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.0719. Min Act: -0.1700
Data Index: 5331252 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9469. Min Range: -6.9469
Max Act: 6.0094. Min Act: -0.1700
Data Index: 6974759 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.9781. Min Act: -0.1700
Data Index: 5257719 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.9469. Min Act: -0.1700
Data Index: 1789263 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.9781. Min Act: -0.1700
Data Index: 655370 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.8844. Min Act: -0.1700
Data Index: 890650 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.8844. Min Act: -0.1700
Data Index: 4263328 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.7906. Min Act: -0.1700
Data Index: 249679 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.7906. Min Act: -0.1700
Data Index: 6129075 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.7906. Min Act: -0.1700
Data Index: 5255688 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.7594. Min Act: -0.1700
Data Index: 118654 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.7594. Min Act: -0.1700
Data Index: 5594113 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.7281. Min Act: -0.1700
Data Index: 5274215 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.6969. Min Act: -0.1700
Data Index: 4600824 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.7281. Min Act: -0.1700
Data Index: 5308837 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.7281. Min Act: -0.1700
Data Index: 6649423 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.6969. Min Act: -0.1700
Data Index: 4576535 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.6656. Min Act: -0.1700
Data Index: 2560350 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9469. Min Range: -6.9469
Max Act: 5.6969. Min Act: -0.1700
Data Index: 7292501 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19