Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2093 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1011. Min Range: -6.1011
Max Act: 6.1011. Min Act: -0.1700
Data Index: 8653776 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1011. Min Range: -6.1011
Max Act: 6.0386. Min Act: -0.1700
Data Index: 6563576 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.9136. Min Act: -0.1700
Data Index: 7301373 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.8824. Min Act: -0.1700
Data Index: 7981474 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.7886. Min Act: -0.1700
Data Index: 3842144 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.7574. Min Act: -0.1700
Data Index: 5459067 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.7261. Min Act: -0.1700
Data Index: 2365633 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.7261. Min Act: -0.1700
Data Index: 1348227 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.7261. Min Act: -0.1700
Data Index: 1382271 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.6949. Min Act: -0.1700
Data Index: 8283738 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.6636. Min Act: -0.1700
Data Index: 1523120 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.6949. Min Act: -0.1700
Data Index: 4299202 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.6011. Min Act: -0.1700
Data Index: 463208 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.6011. Min Act: -0.1700
Data Index: 8032896 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.5699. Min Act: -0.1700
Data Index: 266959 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.5699. Min Act: -0.1700
Data Index: 7121187 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.5699. Min Act: -0.1700
Data Index: 925178 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.5699. Min Act: -0.1700
Data Index: 5442770 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.5699. Min Act: -0.1700
Data Index: 2486363 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1011. Min Range: -6.1011
Max Act: 5.5699. Min Act: -0.1700
Data Index: 978492 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19