Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3790. Min Range: -6.3790
Max Act: 6.3790. Min Act: -0.1700
Data Index: 6489446 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3790. Min Range: -6.3790
Max Act: 6.3790. Min Act: -0.1700
Data Index: 1559671 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3790. Min Range: -6.3790
Max Act: 6.2228. Min Act: -0.1700
Data Index: 4129760 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3790. Min Range: -6.3790
Max Act: 6.0353. Min Act: -0.1700
Data Index: 6557229 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.9728. Min Act: -0.1700
Data Index: 6154722 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.9415. Min Act: -0.1700
Data Index: 4267255 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.9103. Min Act: -0.1700
Data Index: 7408922 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.8478. Min Act: -0.1700
Data Index: 1627781 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.7853. Min Act: -0.1700
Data Index: 6639438 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.8165. Min Act: -0.1700
Data Index: 4850223 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.8165. Min Act: -0.1700
Data Index: 4601084 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.7228. Min Act: -0.1700
Data Index: 2087169 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.7228. Min Act: -0.1700
Data Index: 7621683 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.7228. Min Act: -0.1700
Data Index: 997700 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.7228. Min Act: -0.1700
Data Index: 6037972 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.6603. Min Act: -0.1700
Data Index: 7610960 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.6915. Min Act: -0.1700
Data Index: 8799800 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.6603. Min Act: -0.1700
Data Index: 1678770 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.6915. Min Act: -0.1700
Data Index: 2459937 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3790. Min Range: -6.3790
Max Act: 5.6915. Min Act: -0.1700
Data Index: 6892281 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19