Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2203. Min Range: -6.2203
Max Act: 6.2203. Min Act: -0.1700
Data Index: 1212168 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2203. Min Range: -6.2203
Max Act: 6.1891. Min Act: -0.1700
Data Index: 1212157 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2203. Min Range: -6.2203
Max Act: 6.1578. Min Act: -0.1700
Data Index: 8647827 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2203. Min Range: -6.2203
Max Act: 6.0016. Min Act: -0.1700
Data Index: 1333096 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.9703. Min Act: -0.1700
Data Index: 1333101 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.9078. Min Act: -0.1700
Data Index: 8554663 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.9078. Min Act: -0.1700
Data Index: 5529647 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.8453. Min Act: -0.1700
Data Index: 125638 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.7828. Min Act: -0.1700
Data Index: 3020867 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.7828. Min Act: -0.1700
Data Index: 6981134 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.7203. Min Act: -0.1700
Data Index: 5041349 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.7203. Min Act: -0.1700
Data Index: 4989176 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.7203. Min Act: -0.1700
Data Index: 6920810 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.6891. Min Act: -0.1700
Data Index: 7433711 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.6891. Min Act: -0.1700
Data Index: 3043379 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.6891. Min Act: -0.1700
Data Index: 5956056 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.6266. Min Act: -0.1700
Data Index: 4705093 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.6266. Min Act: -0.1700
Data Index: 413983 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.6266. Min Act: -0.1700
Data Index: 8297050 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2203. Min Range: -6.2203
Max Act: 5.6266. Min Act: -0.1700
Data Index: 3816746 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19