Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1845 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.8592. Min Act: -0.1700
Data Index: 8366257 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.7342. Min Act: -0.1700
Data Index: 8527283 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.3904. Min Act: -0.1700
Data Index: 6795460 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.3592. Min Act: -0.1700
Data Index: 2023016 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.3279. Min Act: -0.1700
Data Index: 5702538 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.3279. Min Act: -0.1700
Data Index: 2883002 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.2029. Min Act: -0.1700
Data Index: 117616 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.1717. Min Act: -0.1700
Data Index: 8468474 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.1092. Min Act: -0.1700
Data Index: 6339892 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.0467. Min Act: -0.1700
Data Index: 5754441 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.0467. Min Act: -0.1700
Data Index: 3646708 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.0467. Min Act: -0.1700
Data Index: 2288374 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8592. Min Range: -6.8592
Max Act: 6.0154. Min Act: -0.1700
Data Index: 901067 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8592. Min Range: -6.8592
Max Act: 5.9842. Min Act: -0.1700
Data Index: 8333020 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8592. Min Range: -6.8592
Max Act: 5.9842. Min Act: -0.1700
Data Index: 709376 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8592. Min Range: -6.8592
Max Act: 5.9529. Min Act: -0.1700
Data Index: 54088 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8592. Min Range: -6.8592
Max Act: 5.9529. Min Act: -0.1700
Data Index: 251483 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8592. Min Range: -6.8592
Max Act: 5.9529. Min Act: -0.1700
Data Index: 306831 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8592. Min Range: -6.8592
Max Act: 5.9217. Min Act: -0.1700
Data Index: 7348091 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8592. Min Range: -6.8592
Max Act: 5.9217. Min Act: -0.1700
Data Index: 3214254 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19