Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2545 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0656. Min Range: -6.0656
Max Act: 6.0656. Min Act: -0.1700
Data Index: 1026835 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0656. Min Range: -6.0656
Max Act: 6.0031. Min Act: -0.1700
Data Index: 4949655 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0656. Min Range: -6.0656
Max Act: 6.0031. Min Act: -0.1700
Data Index: 1026837 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.9094. Min Act: -0.1700
Data Index: 1026833 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.9094. Min Act: -0.1700
Data Index: 7699017 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.9094. Min Act: -0.1700
Data Index: 2698876 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8781. Min Act: -0.1700
Data Index: 8782379 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8781. Min Act: -0.1700
Data Index: 723342 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8469. Min Act: -0.1700
Data Index: 8727646 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8781. Min Act: -0.1700
Data Index: 1026827 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8469. Min Act: -0.1700
Data Index: 1026821 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8469. Min Act: -0.1700
Data Index: 4949654 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8469. Min Act: -0.1700
Data Index: 8224235 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8156. Min Act: -0.1700
Data Index: 8000450 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8156. Min Act: -0.1700
Data Index: 6306051 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.8469. Min Act: -0.1700
Data Index: 1287401 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.7844. Min Act: -0.1700
Data Index: 4949647 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.7844. Min Act: -0.1700
Data Index: 8050287 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.7844. Min Act: -0.1700
Data Index: 8005485 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0656. Min Range: -6.0656
Max Act: 5.7844. Min Act: -0.1700
Data Index: 1026829 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19