Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3911 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.4752. Min Act: -0.1700
Data Index: 4563213 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.3190. Min Act: -0.1700
Data Index: 4023040 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.2565. Min Act: -0.1700
Data Index: 1657907 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.2252. Min Act: -0.1700
Data Index: 5155260 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.2252. Min Act: -0.1700
Data Index: 8269340 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1940. Min Act: -0.1700
Data Index: 232821 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1940. Min Act: -0.1700
Data Index: 8704640 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1940. Min Act: -0.1700
Data Index: 3817032 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1940. Min Act: -0.1700
Data Index: 4038581 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1627. Min Act: -0.1700
Data Index: 1763685 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1002. Min Act: -0.1700
Data Index: 4038579 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1002. Min Act: -0.1700
Data Index: 6205671 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1002. Min Act: -0.1700
Data Index: 4668099 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.1002. Min Act: -0.1700
Data Index: 3307946 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.0690. Min Act: -0.1700
Data Index: 5015724 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.0377. Min Act: -0.1700
Data Index: 3159177 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.0690. Min Act: -0.1700
Data Index: 4066361 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.0377. Min Act: -0.1700
Data Index: 8237189 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4752. Min Range: -5.4752
Max Act: 5.0065. Min Act: -0.1700
Data Index: 8628082 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4752. Min Range: -5.4752
Max Act: 4.9752. Min Act: -0.1700
Data Index: 2136730 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19