Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1858 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.2170. Min Range: -3.2170
Max Act: 3.2170. Min Act: -0.1700
Data Index: 594938 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2170. Min Range: -3.2170
Max Act: 3.1541. Min Act: -0.1700
Data Index: 566375 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2170. Min Range: -3.2170
Max Act: 3.0121. Min Act: -0.1700
Data Index: 541938 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9805. Min Act: -0.1700
Data Index: 847612 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9963. Min Act: -0.1700
Data Index: 547284 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9805. Min Act: -0.1700
Data Index: 444119 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9805. Min Act: -0.1700
Data Index: 370927 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9646. Min Act: -0.1700
Data Index: 502250 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9488. Min Act: -0.1700
Data Index: 238120 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9171. Min Act: -0.1700
Data Index: 351921 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9013. Min Act: -0.1700
Data Index: 395805 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9171. Min Act: -0.1700
Data Index: 690804 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.9171. Min Act: -0.1700
Data Index: 438790 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.8695. Min Act: -0.1700
Data Index: 467395 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.8854. Min Act: -0.1700
Data Index: 307411 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.8854. Min Act: -0.1700
Data Index: 482446 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.8854. Min Act: -0.1700
Data Index: 775856 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.8854. Min Act: -0.1700
Data Index: 1271492 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.8854. Min Act: -0.1700
Data Index: 1532925 (Python Code)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2170. Min Range: -3.2170
Max Act: 2.8695. Min Act: -0.1700
Data Index: 561956 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19