Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 291 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.8305. Min Act: -0.1700
Data Index: 1194830 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.8305. Min Act: -0.1700
Data Index: 884668 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.7367. Min Act: -0.1700
Data Index: 884647 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.7055. Min Act: -0.1699
Data Index: 1564734 (Python Code)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.7055. Min Act: -0.1700
Data Index: 1438016 (Python Code)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.7367. Min Act: -0.1700
Data Index: 243558 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.6117. Min Act: -0.1700
Data Index: 1595104 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.6430. Min Act: -0.1700
Data Index: 775976 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.6430. Min Act: -0.1700
Data Index: 1100111 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.6117. Min Act: -0.1700
Data Index: 1503944 (Python Code)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.6742. Min Act: -0.1700
Data Index: 1462116 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.5805. Min Act: -0.1700
Data Index: 1436872 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.6117. Min Act: -0.1700
Data Index: 1386299 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.6117. Min Act: -0.1700
Data Index: 1446977 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.6117. Min Act: -0.1700
Data Index: 1577231 (Python Code)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.5805. Min Act: -0.1700
Data Index: 448983 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.4867. Min Act: -0.1700
Data Index: 1442014 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.6117. Min Act: -0.1700
Data Index: 1454177 (Python Code)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.5492. Min Act: -0.1700
Data Index: 533307 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8305. Min Range: -4.8305
Max Act: 4.5492. Min Act: -0.1700
Data Index: 1328095 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19