Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.5043. Min Act: -0.1700
Data Index: 1122231 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.5043. Min Act: -0.1700
Data Index: 7963235 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.4731. Min Act: -0.1700
Data Index: 303360 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.4418. Min Act: -0.1700
Data Index: 1122209 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.4106. Min Act: -0.1700
Data Index: 1449253 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.3481. Min Act: -0.1700
Data Index: 4294828 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.3168. Min Act: -0.1700
Data Index: 3604452 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.2856. Min Act: -0.1700
Data Index: 2579055 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.2543. Min Act: -0.1700
Data Index: 8475457 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.2231. Min Act: -0.1700
Data Index: 6170896 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.2543. Min Act: -0.1700
Data Index: 205948 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.1918. Min Act: -0.1700
Data Index: 922787 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.2231. Min Act: -0.1700
Data Index: 7835973 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.1918. Min Act: -0.1700
Data Index: 6873224 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.1918. Min Act: -0.1700
Data Index: 1609496 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.1605. Min Act: -0.1700
Data Index: 7374655 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.1605. Min Act: -0.1700
Data Index: 4220676 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.1293. Min Act: -0.1700
Data Index: 1037674 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.0980. Min Act: -0.1700
Data Index: 5132740 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5043. Min Range: -4.5043
Max Act: 4.0980. Min Act: -0.1700
Data Index: 1265326 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19