Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1978 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.3513. Min Act: -0.1700
Data Index: 786902 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.3826. Min Act: -0.1700
Data Index: 953738 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2888. Min Act: -0.1700
Data Index: 1301914 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2575. Min Act: -0.1700
Data Index: 453576 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2888. Min Act: -0.1700
Data Index: 291290 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.3513. Min Act: -0.1700
Data Index: 714844 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2888. Min Act: -0.1700
Data Index: 618539 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2888. Min Act: -0.1700
Data Index: 129341 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.3201. Min Act: -0.1700
Data Index: 991346 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2575. Min Act: -0.1700
Data Index: 507665 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2263. Min Act: -0.1700
Data Index: 830166 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2263. Min Act: -0.1700
Data Index: 1088380 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2263. Min Act: -0.1700
Data Index: 1262419 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 947152 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.1638. Min Act: -0.1700
Data Index: 597651 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2263. Min Act: -0.1700
Data Index: 222432 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.1325. Min Act: -0.1700
Data Index: 1265202 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.1325. Min Act: -0.1700
Data Index: 443989 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.2263. Min Act: -0.1700
Data Index: 189688 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3826. Min Range: -4.3826
Max Act: 4.1013. Min Act: -0.1700
Data Index: 19343 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19