Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2001 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.8603. Min Act: -0.1700
Data Index: 408774 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.8126. Min Act: -0.1700
Data Index: 597295 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7648. Min Act: -0.1700
Data Index: 215219 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7488. Min Act: -0.1700
Data Index: 912610 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7488. Min Act: -0.1700
Data Index: 135829 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7328. Min Act: -0.1700
Data Index: 229853 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7169. Min Act: -0.1700
Data Index: 211978 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7169. Min Act: -0.1700
Data Index: 940307 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7009. Min Act: -0.1700
Data Index: 49776 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7009. Min Act: -0.1700
Data Index: 1224949 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7009. Min Act: -0.1700
Data Index: 515385 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.6848. Min Act: -0.1700
Data Index: 227843 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7009. Min Act: -0.1700
Data Index: 39926 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7009. Min Act: -0.1700
Data Index: 99329 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.7009. Min Act: -0.1700
Data Index: 639337 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.6848. Min Act: -0.1700
Data Index: 806118 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.6688. Min Act: -0.1700
Data Index: 60644 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.6848. Min Act: -0.1700
Data Index: 1315217 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.6848. Min Act: -0.1700
Data Index: 100815 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8603. Min Range: -2.8603
Max Act: 2.6367. Min Act: -0.1700
Data Index: 59904 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19