Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 688 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.8525. Min Act: -0.1700
Data Index: 169227 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.8056. Min Act: -0.1700
Data Index: 90257 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.8213. Min Act: -0.1700
Data Index: 174497 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7900. Min Act: -0.1700
Data Index: 1237699 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.8056. Min Act: -0.1700
Data Index: 161295 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7587. Min Act: -0.1700
Data Index: 228935 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7430. Min Act: -0.1700
Data Index: 587888 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7900. Min Act: -0.1700
Data Index: 432382 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7743. Min Act: -0.1700
Data Index: 727741 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7743. Min Act: -0.1700
Data Index: 1017950 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7587. Min Act: -0.1700
Data Index: 168991 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7430. Min Act: -0.1700
Data Index: 144975 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7274. Min Act: -0.1700
Data Index: 746273 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7430. Min Act: -0.1700
Data Index: 49625 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7430. Min Act: -0.1700
Data Index: 683733 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7587. Min Act: -0.1700
Data Index: 127718 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6805. Min Act: -0.1700
Data Index: 241313 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.6961. Min Act: -0.1700
Data Index: 531962 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7274. Min Act: -0.1700
Data Index: 389380 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8525. Min Range: -3.8525
Max Act: 3.7117. Min Act: -0.1700
Data Index: 46022 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19