Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 267 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.9895. Min Act: -0.1700
Data Index: 214757 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.9737. Min Act: -0.1700
Data Index: 218006 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.9579. Min Act: -0.1700
Data Index: 1186155 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8945. Min Act: -0.1700
Data Index: 108822 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8786. Min Act: -0.1700
Data Index: 1029547 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8786. Min Act: -0.1700
Data Index: 919003 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8786. Min Act: -0.1700
Data Index: 1073626 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8468. Min Act: -0.1700
Data Index: 457174 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8309. Min Act: -0.1700
Data Index: 120291 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8309. Min Act: -0.1700
Data Index: 1262544 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.7991. Min Act: -0.1700
Data Index: 430550 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8150. Min Act: -0.1700
Data Index: 126697 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8150. Min Act: -0.1700
Data Index: 177112 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.8150. Min Act: -0.1700
Data Index: 246668 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.7832. Min Act: -0.1700
Data Index: 1124321 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.7672. Min Act: -0.1700
Data Index: 1080051 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.7672. Min Act: -0.1700
Data Index: 723506 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.7672. Min Act: -0.1700
Data Index: 573676 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.7513. Min Act: -0.1700
Data Index: 635563 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9895. Min Range: -2.9895
Max Act: 2.7513. Min Act: -0.1700
Data Index: 898519 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19