Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 22 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.8520. Min Act: -0.1700
Data Index: 1490453 (Python Code)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.6645. Min Act: -0.1700
Data Index: 1427192 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.5395. Min Act: -0.1700
Data Index: 1404324 (Python Code)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.6645. Min Act: -0.1700
Data Index: 1608636 (Python Code)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.6020. Min Act: -0.1700
Data Index: 1373503 (Python Code)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.6020. Min Act: -0.1700
Data Index: 1552016 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.5707. Min Act: -0.1700
Data Index: 1088184 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.5707. Min Act: -0.1700
Data Index: 316111 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.5082. Min Act: -0.1700
Data Index: 1514045 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.4770. Min Act: -0.1700
Data Index: 1414098 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.4770. Min Act: -0.1700
Data Index: 1384501 (Python Code)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.5082. Min Act: -0.1700
Data Index: 1632095 (Python Code)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.5082. Min Act: -0.1700
Data Index: 1623892 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.4770. Min Act: -0.1700
Data Index: 1517117 (Python Code)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.5082. Min Act: -0.1700
Data Index: 1109021 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.4770. Min Act: -0.1700
Data Index: 1503777 (Python Code)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.4770. Min Act: -0.1700
Data Index: 824461 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.4145. Min Act: -0.1700
Data Index: 1368458 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.5395. Min Act: -0.1700
Data Index: 1388350 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8520. Min Range: -4.8520
Max Act: 4.4145. Min Act: -0.1700
Data Index: 1447649 (Python Code)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19