Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1876 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4935. Min Act: -0.1700
Data Index: 1542496 (Python Code)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4773. Min Act: -0.1700
Data Index: 1468820 (Python Code)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4611. Min Act: -0.1700
Data Index: 1399754 (Python Code)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4448. Min Act: -0.1700
Data Index: 1619375 (Python Code)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4448. Min Act: -0.1700
Data Index: 1483557 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4448. Min Act: -0.1700
Data Index: 1375346 (Python Code)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4448. Min Act: -0.1700
Data Index: 1539594 (Python Code)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4448. Min Act: -0.1700
Data Index: 1480957 (Python Code)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4448. Min Act: -0.1700
Data Index: 1527207 (Python Code)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4448. Min Act: -0.1700
Data Index: 1644776 (Python Code)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4286. Min Act: -0.1700
Data Index: 1387721 (Python Code)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4286. Min Act: -0.1700
Data Index: 1634186 (Python Code)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4286. Min Act: -0.1700
Data Index: 1609670 (Python Code)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4123. Min Act: -0.1700
Data Index: 1445160 (Python Code)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4123. Min Act: -0.1700
Data Index: 1520190 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4286. Min Act: -0.1700
Data Index: 1608553 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4286. Min Act: -0.1700
Data Index: 1562470 (Python Code)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4286. Min Act: -0.1700
Data Index: 1548533 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4448. Min Act: -0.1700
Data Index: 1544331 (Python Code)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4935. Min Range: -2.4935
Max Act: 2.4123. Min Act: -0.1700
Data Index: 1480443 (Python Code)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19