Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1091 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.9765. Min Act: -0.1700
Data Index: 783394 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0078. Min Range: -4.0078
Max Act: 4.0078. Min Act: -0.1700
Data Index: 823022 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.9453. Min Act: -0.1700
Data Index: 183528 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.9140. Min Act: -0.1700
Data Index: 1150153 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.9140. Min Act: -0.1700
Data Index: 1035642 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.8827. Min Act: -0.1700
Data Index: 1197158 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.8515. Min Act: -0.1700
Data Index: 1322602 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.8202. Min Act: -0.1700
Data Index: 1337665 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.8515. Min Act: -0.1700
Data Index: 1041955 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.8515. Min Act: -0.1700
Data Index: 728049 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.8202. Min Act: -0.1700
Data Index: 83588 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.7889. Min Act: -0.1700
Data Index: 1352286 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.8202. Min Act: -0.1700
Data Index: 927003 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.7889. Min Act: -0.1700
Data Index: 206553 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.7889. Min Act: -0.1700
Data Index: 252484 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.8202. Min Act: -0.1700
Data Index: 1134343 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.7576. Min Act: -0.1700
Data Index: 939602 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.7889. Min Act: -0.1700
Data Index: 527653 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.7889. Min Act: -0.1700
Data Index: 422350 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0078. Min Range: -4.0078
Max Act: 3.7576. Min Act: -0.1700
Data Index: 353061 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19