Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 32 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.8573. Min Act: -0.1700
Data Index: 804097 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.7948. Min Act: -0.1700
Data Index: 520880 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.7948. Min Act: -0.1700
Data Index: 202415 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.7948. Min Act: -0.1698
Data Index: 61585 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.7635. Min Act: -0.1699
Data Index: 1208476 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.7948. Min Act: -0.1700
Data Index: 624235 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.7323. Min Act: -0.1700
Data Index: 1062265 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.7010. Min Act: -0.1700
Data Index: 1021893 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.6385. Min Act: -0.1700
Data Index: 628407 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.6698. Min Act: -0.1700
Data Index: 1157292 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.6385. Min Act: -0.1700
Data Index: 82278 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.6385. Min Act: -0.1700
Data Index: 302340 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.6073. Min Act: -0.1700
Data Index: 113732 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.6073. Min Act: -0.1700
Data Index: 886528 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.5760. Min Act: -0.1700
Data Index: 688230 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.6385. Min Act: -0.1700
Data Index: 289432 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.6385. Min Act: -0.1700
Data Index: 450191 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.5760. Min Act: -0.1700
Data Index: 134014 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.5760. Min Act: -0.1700
Data Index: 132628 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8573. Min Range: -4.8573
Max Act: 4.5448. Min Act: -0.1700
Data Index: 712177 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19