Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1443 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2516. Min Range: -7.2516
Max Act: 7.2516. Min Act: -0.1700
Data Index: 48323 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2516. Min Range: -7.2516
Max Act: 7.1266. Min Act: -0.1700
Data Index: 7151548 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2516. Min Range: -7.2516
Max Act: 7.0953. Min Act: -0.1700
Data Index: 2989606 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.9703. Min Act: -0.1700
Data Index: 2473806 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.9391. Min Act: -0.1700
Data Index: 3007630 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.9078. Min Act: -0.1700
Data Index: 8673041 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.9078. Min Act: -0.1700
Data Index: 2540908 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.8766. Min Act: -0.1700
Data Index: 7433721 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.8141. Min Act: -0.1700
Data Index: 4208356 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.8453. Min Act: -0.1700
Data Index: 6282281 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.7828. Min Act: -0.1700
Data Index: 2985291 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.7828. Min Act: -0.1700
Data Index: 7338602 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.7828. Min Act: -0.1700
Data Index: 4488571 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.7516. Min Act: -0.1700
Data Index: 1463137 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.7203. Min Act: -0.1700
Data Index: 7579939 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.7828. Min Act: -0.1700
Data Index: 4111265 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.7516. Min Act: -0.1700
Data Index: 4347621 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.6891. Min Act: -0.1700
Data Index: 7579936 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.7203. Min Act: -0.1700
Data Index: 179348 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2516. Min Range: -7.2516
Max Act: 6.6891. Min Act: -0.1700
Data Index: 1654639 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19