Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 9 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2967. Min Range: -3.2967
Max Act: 3.2967. Min Act: -0.1700
Data Index: 1456491 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2967. Min Range: -3.2967
Max Act: 3.2024. Min Act: -0.1700
Data Index: 1649439 (Python Code)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2967. Min Range: -3.2967
Max Act: 3.1394. Min Act: -0.1700
Data Index: 908555 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2967. Min Range: -3.2967
Max Act: 3.1079. Min Act: -0.1700
Data Index: 1360745 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2967. Min Range: -3.2967
Max Act: 3.0606. Min Act: -0.1700
Data Index: 200763 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2967. Min Range: -3.2967
Max Act: 3.0606. Min Act: -0.1700
Data Index: 1527475 (Python Code)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2967. Min Range: -3.2967
Max Act: 3.0132. Min Act: -0.1700
Data Index: 135359 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9657. Min Act: -0.1700
Data Index: 1647350 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9657. Min Act: -0.1700
Data Index: 1096345 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9816. Min Act: -0.1700
Data Index: 904192 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9657. Min Act: -0.1700
Data Index: 75555 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9499. Min Act: -0.1700
Data Index: 566571 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9499. Min Act: -0.1700
Data Index: 1107581 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9499. Min Act: -0.1700
Data Index: 668133 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9657. Min Act: -0.1700
Data Index: 1284939 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9499. Min Act: -0.1700
Data Index: 1045499 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9341. Min Act: -0.1700
Data Index: 1500488 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9657. Min Act: -0.1700
Data Index: 1580372 (Python Code)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9657. Min Act: -0.1700
Data Index: 1227385 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2967. Min Range: -3.2967
Max Act: 2.9499. Min Act: -0.1700
Data Index: 705552 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19