Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1593 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.0092. Min Range: -4.0092
Max Act: 4.0092. Min Act: -0.1700
Data Index: 372806 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0092. Min Range: -4.0092
Max Act: 4.0092. Min Act: -0.1700
Data Index: 1146020 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.9779. Min Act: -0.1700
Data Index: 170802 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0092. Min Range: -4.0092
Max Act: 4.0092. Min Act: -0.1700
Data Index: 643134 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.9154. Min Act: -0.1700
Data Index: 1107683 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.9154. Min Act: -0.1700
Data Index: 1039715 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8841. Min Act: -0.1700
Data Index: 261653 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8841. Min Act: -0.1700
Data Index: 1121754 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.9154. Min Act: -0.1700
Data Index: 71325 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8529. Min Act: -0.1700
Data Index: 1230676 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8216. Min Act: -0.1700
Data Index: 569143 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8529. Min Act: -0.1700
Data Index: 65533 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8216. Min Act: -0.1700
Data Index: 662625 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8529. Min Act: -0.1700
Data Index: 1228884 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8529. Min Act: -0.1700
Data Index: 26058 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8529. Min Act: -0.1700
Data Index: 354270 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8529. Min Act: -0.1699
Data Index: 1066895 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8216. Min Act: -0.1700
Data Index: 440582 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.7903. Min Act: -0.1700
Data Index: 676681 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0092. Min Range: -4.0092
Max Act: 3.8216. Min Act: -0.1700
Data Index: 1198245 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19