Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 422 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0392. Min Range: -8.0392
Max Act: 8.0392. Min Act: -0.1700
Data Index: 7569620 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.6955. Min Act: -0.1700
Data Index: 2387074 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.6330. Min Act: -0.1700
Data Index: 205854 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.6017. Min Act: -0.1700
Data Index: 6170185 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.6017. Min Act: -0.1700
Data Index: 2078492 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5705. Min Act: -0.1700
Data Index: 847451 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5705. Min Act: -0.1700
Data Index: 575167 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5705. Min Act: -0.1700
Data Index: 361966 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5705. Min Act: -0.1700
Data Index: 6596554 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5705. Min Act: -0.1700
Data Index: 566424 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5392. Min Act: -0.1700
Data Index: 1203651 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5392. Min Act: -0.1700
Data Index: 8779354 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5705. Min Act: -0.1700
Data Index: 447491 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5392. Min Act: -0.1700
Data Index: 1555310 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5392. Min Act: -0.1700
Data Index: 3651044 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5080. Min Act: -0.1700
Data Index: 7458164 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5080. Min Act: -0.1700
Data Index: 4655544 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.4767. Min Act: -0.1700
Data Index: 7848 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.5080. Min Act: -0.1700
Data Index: 4592276 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0392. Min Range: -8.0392
Max Act: 7.4767. Min Act: -0.1700
Data Index: 258263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19