Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4787. Min Range: -8.4787
Max Act: 8.4787. Min Act: -0.1700
Data Index: 1903036 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4787. Min Range: -8.4787
Max Act: 8.0412. Min Act: -0.1700
Data Index: 2986618 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4787. Min Range: -8.4787
Max Act: 8.0100. Min Act: -0.1700
Data Index: 5706413 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4787. Min Range: -8.4787
Max Act: 8.0100. Min Act: -0.1700
Data Index: 2559913 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.9787. Min Act: -0.1700
Data Index: 1145454 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.8537. Min Act: -0.1700
Data Index: 5893464 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.7600. Min Act: -0.1700
Data Index: 6426530 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.7287. Min Act: -0.1700
Data Index: 5239150 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.6662. Min Act: -0.1700
Data Index: 7581260 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.6662. Min Act: -0.1700
Data Index: 2345576 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.6662. Min Act: -0.1700
Data Index: 8089504 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.6037. Min Act: -0.1700
Data Index: 1142745 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.6037. Min Act: -0.1700
Data Index: 7104391 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.5725. Min Act: -0.1700
Data Index: 583511 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.6037. Min Act: -0.1700
Data Index: 2566221 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.6350. Min Act: -0.1700
Data Index: 6128212 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.6350. Min Act: -0.1700
Data Index: 3642230 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.5100. Min Act: -0.1700
Data Index: 1671718 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.6037. Min Act: -0.1700
Data Index: 4939542 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4787. Min Range: -8.4787
Max Act: 7.5725. Min Act: -0.1700
Data Index: 2750978 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19