Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.7407. Min Act: -0.1700
Data Index: 803923 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.5220. Min Act: -0.1700
Data Index: 1076239 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.3970. Min Act: -0.1700
Data Index: 3318883 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.3970. Min Act: -0.1700
Data Index: 1725956 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.3657. Min Act: -0.1700
Data Index: 1908521 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.2720. Min Act: -0.1700
Data Index: 3808302 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.2407. Min Act: -0.1700
Data Index: 484027 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1782. Min Act: -0.1700
Data Index: 2046145 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.2095. Min Act: -0.1700
Data Index: 7504711 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.2095. Min Act: -0.1700
Data Index: 1194990 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1782. Min Act: -0.1700
Data Index: 8676703 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1470. Min Act: -0.1700
Data Index: 268222 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.2095. Min Act: -0.1700
Data Index: 3360215 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1470. Min Act: -0.1700
Data Index: 7276422 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1470. Min Act: -0.1700
Data Index: 861801 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1470. Min Act: -0.1700
Data Index: 1913388 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1157. Min Act: -0.1700
Data Index: 7861473 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1157. Min Act: -0.1700
Data Index: 3785420 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1157. Min Act: -0.1700
Data Index: 5017067 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7407. Min Range: -6.7407
Max Act: 6.1157. Min Act: -0.1700
Data Index: 522468 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19