Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.1281. Min Act: -0.1700
Data Index: 260507 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.1114. Min Act: -0.1700
Data Index: 3263546 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.1114. Min Act: -0.1700
Data Index: 5366839 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0947. Min Act: -0.1700
Data Index: 3636979 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0611. Min Act: -0.1700
Data Index: 4147134 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0611. Min Act: -0.1700
Data Index: 614487 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0443. Min Act: -0.1700
Data Index: 6991894 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0611. Min Act: -0.1700
Data Index: 5995741 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0443. Min Act: -0.1700
Data Index: 8710049 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0275. Min Act: -0.1700
Data Index: 284364 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0275. Min Act: -0.1700
Data Index: 3841407 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0443. Min Act: -0.1700
Data Index: 2982517 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0443. Min Act: -0.1700
Data Index: 3884236 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0275. Min Act: -0.1700
Data Index: 3193616 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0275. Min Act: -0.1700
Data Index: 7545264 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0275. Min Act: -0.1700
Data Index: 2468645 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0443. Min Act: -0.1700
Data Index: 7364673 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0275. Min Act: -0.1700
Data Index: 5226155 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1281. Min Range: -2.1281
Max Act: 1.9937. Min Act: -0.1700
Data Index: 2913472 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1281. Min Range: -2.1281
Max Act: 2.0106. Min Act: -0.1700
Data Index: 4490501 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19