Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1547 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.4790. Min Range: -6.4790
Max Act: 6.4790. Min Act: -0.1700
Data Index: 1560844 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4790. Min Range: -6.4790
Max Act: 6.4165. Min Act: -0.1700
Data Index: 1367323 (Python Code)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4790. Min Range: -6.4790
Max Act: 6.2290. Min Act: -0.1699
Data Index: 1508972 (Python Code)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4790. Min Range: -6.4790
Max Act: 6.1665. Min Act: -0.1700
Data Index: 1564301 (Python Code)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4790. Min Range: -6.4790
Max Act: 6.0415. Min Act: -0.1700
Data Index: 1395021 (Python Code)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.9790. Min Act: -0.1699
Data Index: 1528372 (Python Code)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4790. Min Range: -6.4790
Max Act: 6.0727. Min Act: -0.1698
Data Index: 1395929 (Python Code)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4790. Min Range: -6.4790
Max Act: 6.0727. Min Act: -0.1699
Data Index: 1358996 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.9477. Min Act: -0.1700
Data Index: 1575041 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.9165. Min Act: -0.1699
Data Index: 1618556 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.9477. Min Act: -0.1699
Data Index: 1509687 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.8227. Min Act: -0.1698
Data Index: 1631612 (Python Code)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.8540. Min Act: -0.1700
Data Index: 1510191 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.8227. Min Act: -0.1700
Data Index: 1438902 (Python Code)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.8540. Min Act: -0.1700
Data Index: 1399718 (Python Code)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.6977. Min Act: -0.1700
Data Index: 1395503 (Python Code)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.6977. Min Act: -0.1700
Data Index: 1636274 (Python Code)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1588061 (Python Code)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.7915. Min Act: -0.1699
Data Index: 1509508 (Python Code)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4790. Min Range: -6.4790
Max Act: 5.6977. Min Act: -0.1700
Data Index: 1515174 (Python Code)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19