Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3925 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.6619. Min Act: -0.1700
Data Index: 138682 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.6619. Min Act: -0.1700
Data Index: 1513252 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.6463. Min Act: -0.1700
Data Index: 4937579 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.6306. Min Act: -0.1700
Data Index: 6003268 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5680. Min Act: -0.1700
Data Index: 6985994 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5680. Min Act: -0.1700
Data Index: 5708979 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5524. Min Act: -0.1700
Data Index: 2272655 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5210. Min Act: -0.1700
Data Index: 3270642 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5210. Min Act: -0.1700
Data Index: 790105 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5054. Min Act: -0.1700
Data Index: 7270547 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5210. Min Act: -0.1700
Data Index: 8306649 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5367. Min Act: -0.1700
Data Index: 4982494 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5210. Min Act: -0.1700
Data Index: 5007754 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5054. Min Act: -0.1700
Data Index: 5809676 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5054. Min Act: -0.1700
Data Index: 8385924 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5054. Min Act: -0.1700
Data Index: 8432786 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5210. Min Act: -0.1700
Data Index: 6479030 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5054. Min Act: -0.1700
Data Index: 5602969 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.4897. Min Act: -0.1700
Data Index: 5435980 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6619. Min Range: -3.6619
Max Act: 3.5054. Min Act: -0.1700
Data Index: 6526235 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19