Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2953 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1578. Min Range: -6.1578
Max Act: 6.1578. Min Act: -0.1700
Data Index: 748303 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1578. Min Range: -6.1578
Max Act: 6.0953. Min Act: -0.1700
Data Index: 667157 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1578. Min Range: -6.1578
Max Act: 6.0328. Min Act: -0.1700
Data Index: 1961865 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1578. Min Range: -6.1578
Max Act: 6.0328. Min Act: -0.1700
Data Index: 7230195 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1578. Min Range: -6.1578
Max Act: 6.0328. Min Act: -0.1700
Data Index: 418983 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.9078. Min Act: -0.1700
Data Index: 1790379 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.9391. Min Act: -0.1700
Data Index: 3718265 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.9078. Min Act: -0.1700
Data Index: 1448809 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.9078. Min Act: -0.1700
Data Index: 559445 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.8766. Min Act: -0.1700
Data Index: 5404539 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.9078. Min Act: -0.1700
Data Index: 2203697 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.8766. Min Act: -0.1700
Data Index: 804623 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.8766. Min Act: -0.1700
Data Index: 7923869 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.8766. Min Act: -0.1700
Data Index: 114962 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.8453. Min Act: -0.1700
Data Index: 3843844 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.8453. Min Act: -0.1700
Data Index: 5231276 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.7828. Min Act: -0.1700
Data Index: 1452683 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.8141. Min Act: -0.1700
Data Index: 4048905 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.8141. Min Act: -0.1700
Data Index: 5492928 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1578. Min Range: -6.1578
Max Act: 5.8141. Min Act: -0.1700
Data Index: 1231820 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19