Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2024 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.8145. Min Act: -0.1700
Data Index: 907748 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.7832. Min Act: -0.1700
Data Index: 1356525 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.7520. Min Act: -0.1700
Data Index: 556638 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.7832. Min Act: -0.1700
Data Index: 315132 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.7207. Min Act: -0.1700
Data Index: 241620 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.6582. Min Act: -0.1700
Data Index: 1073787 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.6270. Min Act: -0.1700
Data Index: 233919 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5957. Min Act: -0.1700
Data Index: 1105924 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5332. Min Act: -0.1700
Data Index: 144495 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5957. Min Act: -0.1700
Data Index: 482593 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5957. Min Act: -0.1700
Data Index: 284809 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5020. Min Act: -0.1700
Data Index: 1174165 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5332. Min Act: -0.1700
Data Index: 1031739 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5332. Min Act: -0.1700
Data Index: 31172 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5332. Min Act: -0.1700
Data Index: 385514 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5332. Min Act: -0.1700
Data Index: 906918 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5020. Min Act: -0.1700
Data Index: 216830 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5020. Min Act: -0.1700
Data Index: 1269602 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.5020. Min Act: -0.1700
Data Index: 805375 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8145. Min Range: -4.8145
Max Act: 4.4707. Min Act: -0.1700
Data Index: 627381 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19