Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 864 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.2250. Min Act: -0.1700
Data Index: 856966 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.2084. Min Act: -0.1700
Data Index: 688852 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1918. Min Act: -0.1700
Data Index: 703607 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.2084. Min Act: -0.1700
Data Index: 776293 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1752. Min Act: -0.1700
Data Index: 90248 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1586. Min Act: -0.1700
Data Index: 475414 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1586. Min Act: -0.1700
Data Index: 1324063 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1419. Min Act: -0.1700
Data Index: 1029302 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1336. Min Act: -0.1700
Data Index: 352581 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1336. Min Act: -0.1700
Data Index: 1147074 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1586. Min Act: -0.1700
Data Index: 376249 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1169. Min Act: -0.1700
Data Index: 1177351 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1252. Min Act: -0.1700
Data Index: 924749 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1085. Min Act: -0.1700
Data Index: 362 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1169. Min Act: -0.1700
Data Index: 135162 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1002. Min Act: -0.1700
Data Index: 174978 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.0918. Min Act: -0.1700
Data Index: 145760 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1002. Min Act: -0.1700
Data Index: 314257 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1252. Min Act: -0.1700
Data Index: 824372 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2250. Min Range: -2.2250
Max Act: 2.1002. Min Act: -0.1700
Data Index: 1062400 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19