Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1312. Min Range: -8.1312
Max Act: 8.1312. Min Act: -0.1700
Data Index: 8195246 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1312. Min Range: -8.1312
Max Act: 8.1000. Min Act: -0.1700
Data Index: 7778802 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1312. Min Range: -8.1312
Max Act: 8.1000. Min Act: -0.1700
Data Index: 5820645 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1312. Min Range: -8.1312
Max Act: 8.0375. Min Act: -0.1700
Data Index: 6822816 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1312. Min Range: -8.1312
Max Act: 8.0375. Min Act: -0.1700
Data Index: 6801258 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1312. Min Range: -8.1312
Max Act: 8.0062. Min Act: -0.1700
Data Index: 7648840 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1312. Min Range: -8.1312
Max Act: 8.0062. Min Act: -0.1700
Data Index: 6774920 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1312. Min Range: -8.1312
Max Act: 8.0062. Min Act: -0.1700
Data Index: 8382616 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1312. Min Range: -8.1312
Max Act: 8.0062. Min Act: -0.1700
Data Index: 2589980 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.9437. Min Act: -0.1700
Data Index: 5037622 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.9437. Min Act: -0.1700
Data Index: 4247555 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.8812. Min Act: -0.1700
Data Index: 4247568 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.8500. Min Act: -0.1700
Data Index: 6053856 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.8812. Min Act: -0.1700
Data Index: 3073863 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.8500. Min Act: -0.1700
Data Index: 8571771 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.8500. Min Act: -0.1700
Data Index: 6331949 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.8812. Min Act: -0.1700
Data Index: 2310010 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.8500. Min Act: -0.1700
Data Index: 3266279 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.8500. Min Act: -0.1700
Data Index: 2434067 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1312. Min Range: -8.1312
Max Act: 7.8500. Min Act: -0.1700
Data Index: 1796333 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19