Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.8415. Min Act: -0.1700
Data Index: 1637919 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.7790. Min Act: -0.1700
Data Index: 806520 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.7790. Min Act: -0.1700
Data Index: 3644955 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.8103. Min Act: -0.1700
Data Index: 1339425 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.7478. Min Act: -0.1700
Data Index: 5794873 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6853. Min Act: -0.1700
Data Index: 4436562 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6853. Min Act: -0.1700
Data Index: 7837224 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.7165. Min Act: -0.1700
Data Index: 8169268 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6853. Min Act: -0.1700
Data Index: 1270503 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6853. Min Act: -0.1700
Data Index: 3118237 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6853. Min Act: -0.1700
Data Index: 5274505 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6853. Min Act: -0.1700
Data Index: 599010 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6228. Min Act: -0.1700
Data Index: 5396243 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6540. Min Act: -0.1700
Data Index: 2760325 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6540. Min Act: -0.1700
Data Index: 5893862 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6540. Min Act: -0.1700
Data Index: 6556288 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6228. Min Act: -0.1700
Data Index: 5260696 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6540. Min Act: -0.1700
Data Index: 7091358 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6540. Min Act: -0.1700
Data Index: 7182202 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8415. Min Range: -4.8415
Max Act: 4.6228. Min Act: -0.1700
Data Index: 2464063 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19