Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1379. Min Range: -6.1379
Max Act: 6.1379. Min Act: -0.1700
Data Index: 7949889 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.8879. Min Act: -0.1700
Data Index: 1639801 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.8879. Min Act: -0.1700
Data Index: 1330121 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.8254. Min Act: -0.1700
Data Index: 6243021 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.7317. Min Act: -0.1700
Data Index: 6368411 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.7004. Min Act: -0.1700
Data Index: 4344255 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.7004. Min Act: -0.1700
Data Index: 2368827 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.7004. Min Act: -0.1700
Data Index: 1917473 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6692. Min Act: -0.1700
Data Index: 8644914 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.7004. Min Act: -0.1700
Data Index: 7104463 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6379. Min Act: -0.1700
Data Index: 5788106 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6379. Min Act: -0.1700
Data Index: 4381929 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6379. Min Act: -0.1700
Data Index: 7992146 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6067. Min Act: -0.1700
Data Index: 3936180 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6379. Min Act: -0.1700
Data Index: 1923938 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6379. Min Act: -0.1700
Data Index: 1364813 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6067. Min Act: -0.1700
Data Index: 8686867 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.6067. Min Act: -0.1700
Data Index: 2532365 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5754. Min Act: -0.1700
Data Index: 7302464 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1379. Min Range: -6.1379
Max Act: 5.5754. Min Act: -0.1700
Data Index: 3293397 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19