Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3141 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1037. Min Range: -4.1037
Max Act: 4.1037. Min Act: -0.1700
Data Index: 577514 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1037. Min Range: -4.1037
Max Act: 4.1037. Min Act: -0.1700
Data Index: 5343346 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1037. Min Range: -4.1037
Max Act: 4.0724. Min Act: -0.1700
Data Index: 32783 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1037. Min Range: -4.1037
Max Act: 4.0099. Min Act: -0.1700
Data Index: 7166663 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1037. Min Range: -4.1037
Max Act: 4.0099. Min Act: -0.1700
Data Index: 8108655 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9787. Min Act: -0.1700
Data Index: 6662273 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9161. Min Act: -0.1700
Data Index: 4006849 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9474. Min Act: -0.1700
Data Index: 7907912 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9474. Min Act: -0.1700
Data Index: 6979284 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9474. Min Act: -0.1700
Data Index: 5401096 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9474. Min Act: -0.1700
Data Index: 1402926 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9474. Min Act: -0.1700
Data Index: 5619722 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9161. Min Act: -0.1700
Data Index: 5929096 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9161. Min Act: -0.1700
Data Index: 3478671 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.8849. Min Act: -0.1700
Data Index: 6728688 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.9161. Min Act: -0.1700
Data Index: 3913726 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.8536. Min Act: -0.1700
Data Index: 3048310 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.8849. Min Act: -0.1700
Data Index: 5466146 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.8380. Min Act: -0.1700
Data Index: 3386208 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1037. Min Range: -4.1037
Max Act: 3.8536. Min Act: -0.1700
Data Index: 7011618 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19