Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4523 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.3702. Min Act: -0.1700
Data Index: 6748970 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.3389. Min Act: -0.1700
Data Index: 1613105 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.1827. Min Act: -0.1700
Data Index: 2846524 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.1514. Min Act: -0.1700
Data Index: 381356 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.1514. Min Act: -0.1700
Data Index: 6345914 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.0889. Min Act: -0.1700
Data Index: 4798649 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.0889. Min Act: -0.1700
Data Index: 3414005 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.0577. Min Act: -0.1700
Data Index: 7150872 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.0264. Min Act: -0.1700
Data Index: 5638927 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.0577. Min Act: -0.1700
Data Index: 5411655 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.0577. Min Act: -0.1700
Data Index: 5295456 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.0264. Min Act: -0.1700
Data Index: 6078176 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.0264. Min Act: -0.1700
Data Index: 1967705 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3702. Min Range: -5.3702
Max Act: 5.0264. Min Act: -0.1700
Data Index: 2341914 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3702. Min Range: -5.3702
Max Act: 4.9952. Min Act: -0.1700
Data Index: 8055664 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3702. Min Range: -5.3702
Max Act: 4.9952. Min Act: -0.1700
Data Index: 7873664 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3702. Min Range: -5.3702
Max Act: 4.9952. Min Act: -0.1700
Data Index: 3020175 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3702. Min Range: -5.3702
Max Act: 4.9639. Min Act: -0.1700
Data Index: 3445541 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3702. Min Range: -5.3702
Max Act: 4.9639. Min Act: -0.1700
Data Index: 6559481 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3702. Min Range: -5.3702
Max Act: 4.9639. Min Act: -0.1700
Data Index: 7068589 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19