Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.5849. Min Act: -0.1700
Data Index: 2430893 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.4911. Min Act: -0.1700
Data Index: 7321684 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.4599. Min Act: -0.1700
Data Index: 2057853 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.4286. Min Act: -0.1700
Data Index: 3702904 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.3661. Min Act: -0.1700
Data Index: 6982382 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.3661. Min Act: -0.1700
Data Index: 2834036 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.3661. Min Act: -0.1700
Data Index: 308722 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.3349. Min Act: -0.1700
Data Index: 57463 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.3036. Min Act: -0.1700
Data Index: 1967960 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2724. Min Act: -0.1700
Data Index: 3491286 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2724. Min Act: -0.1700
Data Index: 2968652 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2724. Min Act: -0.1700
Data Index: 8343357 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2724. Min Act: -0.1700
Data Index: 4000929 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2724. Min Act: -0.1700
Data Index: 4312504 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2411. Min Act: -0.1700
Data Index: 7613654 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.1786. Min Act: -0.1700
Data Index: 2070873 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2411. Min Act: -0.1700
Data Index: 7335212 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2099. Min Act: -0.1700
Data Index: 2057854 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2099. Min Act: -0.1700
Data Index: 7663622 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5849. Min Range: -5.5849
Max Act: 5.2099. Min Act: -0.1700
Data Index: 7663619 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19