Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 750 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1020. Min Range: -8.1020
Max Act: 8.1020. Min Act: -0.1700
Data Index: 3774767 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.9770. Min Act: -0.1700
Data Index: 5230139 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.9770. Min Act: -0.1700
Data Index: 4631848 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.8520. Min Act: -0.1700
Data Index: 857361 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.8520. Min Act: -0.1700
Data Index: 8548593 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.7270. Min Act: -0.1700
Data Index: 3088648 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.7270. Min Act: -0.1700
Data Index: 633901 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.7270. Min Act: -0.1700
Data Index: 8413828 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.6645. Min Act: -0.1700
Data Index: 4688432 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.6645. Min Act: -0.1700
Data Index: 1537786 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.6645. Min Act: -0.1700
Data Index: 7484561 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.6020. Min Act: -0.1700
Data Index: 2375183 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.5395. Min Act: -0.1700
Data Index: 4929777 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.6020. Min Act: -0.1700
Data Index: 3477523 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.5395. Min Act: -0.1700
Data Index: 8282101 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.5395. Min Act: -0.1700
Data Index: 3701726 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.4770. Min Act: -0.1700
Data Index: 2275146 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.4770. Min Act: -0.1700
Data Index: 8655773 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.4770. Min Act: -0.1700
Data Index: 7730388 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1020. Min Range: -8.1020
Max Act: 7.4145. Min Act: -0.1700
Data Index: 6653452 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19