Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 30 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.3391. Min Act: -0.1700
Data Index: 1194700 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.3391. Min Act: -0.1700
Data Index: 934827 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.4016. Min Act: -0.1700
Data Index: 398506 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.3391. Min Act: -0.1700
Data Index: 156891 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.3078. Min Act: -0.1700
Data Index: 813273 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.3078. Min Act: -0.1700
Data Index: 588677 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2453. Min Act: -0.1700
Data Index: 286995 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2453. Min Act: -0.1700
Data Index: 317123 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2766. Min Act: -0.1700
Data Index: 754936 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2766. Min Act: -0.1700
Data Index: 171458 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2453. Min Act: -0.1700
Data Index: 932513 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2453. Min Act: -0.1700
Data Index: 812032 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2453. Min Act: -0.1700
Data Index: 682628 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2141. Min Act: -0.1700
Data Index: 222689 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.1828. Min Act: -0.1700
Data Index: 966607 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2453. Min Act: -0.1700
Data Index: 516467 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.2141. Min Act: -0.1700
Data Index: 301193 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.1828. Min Act: -0.1700
Data Index: 800179 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.1516. Min Act: -0.1700
Data Index: 372038 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4016. Min Range: -4.4016
Max Act: 4.1203. Min Act: -0.1700
Data Index: 280964 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19