Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1998 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.7572. Min Act: -0.1700
Data Index: 1369743 (Python Code)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.6291. Min Act: -0.1700
Data Index: 1176949 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.6291. Min Act: -0.1700
Data Index: 1442440 (Python Code)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5808. Min Act: -0.1700
Data Index: 194836 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5647. Min Act: -0.1700
Data Index: 1455700 (Python Code)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5647. Min Act: -0.1700
Data Index: 1431274 (Python Code)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5969. Min Act: -0.1700
Data Index: 1287929 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5324. Min Act: -0.1700
Data Index: 1365363 (Python Code)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5324. Min Act: -0.1700
Data Index: 1533707 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5162. Min Act: -0.1700
Data Index: 333412 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5162. Min Act: -0.1700
Data Index: 1578005 (Python Code)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5162. Min Act: -0.1700
Data Index: 1582265 (Python Code)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5162. Min Act: -0.1700
Data Index: 725954 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5162. Min Act: -0.1700
Data Index: 1197558 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5162. Min Act: -0.1700
Data Index: 1517690 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5001. Min Act: -0.1699
Data Index: 1644563 (Python Code)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.5001. Min Act: -0.1700
Data Index: 385330 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.4676. Min Act: -0.1699
Data Index: 1577396 (Python Code)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.4676. Min Act: -0.1700
Data Index: 1599029 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7572. Min Range: -2.7572
Max Act: 2.4676. Min Act: -0.1700
Data Index: 789207 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19