Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2404 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.2561. Min Act: -0.1700
Data Index: 6125820 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1936. Min Act: -0.1700
Data Index: 2036598 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1936. Min Act: -0.1700
Data Index: 6335063 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1936. Min Act: -0.1700
Data Index: 4380878 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1624. Min Act: -0.1700
Data Index: 3710041 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1311. Min Act: -0.1700
Data Index: 8336903 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1311. Min Act: -0.1700
Data Index: 1242692 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1311. Min Act: -0.1700
Data Index: 7769447 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1311. Min Act: -0.1700
Data Index: 2462204 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1311. Min Act: -0.1700
Data Index: 1603368 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.1311. Min Act: -0.1700
Data Index: 5880432 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.0999. Min Act: -0.1700
Data Index: 3442450 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.0999. Min Act: -0.1700
Data Index: 6818422 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.0999. Min Act: -0.1700
Data Index: 4147174 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.0686. Min Act: -0.1700
Data Index: 6771939 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.0686. Min Act: -0.1700
Data Index: 4658331 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.0686. Min Act: -0.1700
Data Index: 7057170 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.0686. Min Act: -0.1700
Data Index: 7295657 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.0686. Min Act: -0.1700
Data Index: 5617357 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2561. Min Range: -5.2561
Max Act: 5.0999. Min Act: -0.1700
Data Index: 2812000 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19