Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3047 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4002. Min Range: -7.4002
Max Act: 7.4002. Min Act: -0.1700
Data Index: 1039200 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4002. Min Range: -7.4002
Max Act: 7.2752. Min Act: -0.1700
Data Index: 5096677 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4002. Min Range: -7.4002
Max Act: 7.2440. Min Act: -0.1700
Data Index: 5084052 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4002. Min Range: -7.4002
Max Act: 7.2127. Min Act: -0.1700
Data Index: 4022677 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4002. Min Range: -7.4002
Max Act: 7.1502. Min Act: -0.1700
Data Index: 1512196 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4002. Min Range: -7.4002
Max Act: 7.0877. Min Act: -0.1700
Data Index: 4043678 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4002. Min Range: -7.4002
Max Act: 7.1190. Min Act: -0.1700
Data Index: 350541 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4002. Min Range: -7.4002
Max Act: 7.0252. Min Act: -0.1700
Data Index: 823539 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9940. Min Act: -0.1700
Data Index: 4652301 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9940. Min Act: -0.1700
Data Index: 3155040 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9940. Min Act: -0.1700
Data Index: 88644 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9627. Min Act: -0.1700
Data Index: 8559754 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9627. Min Act: -0.1700
Data Index: 8597510 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9940. Min Act: -0.1700
Data Index: 6239199 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9627. Min Act: -0.1700
Data Index: 4101724 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9315. Min Act: -0.1700
Data Index: 5041778 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9315. Min Act: -0.1700
Data Index: 2419893 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9627. Min Act: -0.1700
Data Index: 6734018 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9315. Min Act: -0.1700
Data Index: 728148 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4002. Min Range: -7.4002
Max Act: 6.9002. Min Act: -0.1700
Data Index: 4008598 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19