Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 112 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.9276. Min Act: -0.1700
Data Index: 1604227 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.9117. Min Act: -0.1700
Data Index: 1409118 (Python Code)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8641. Min Act: -0.1700
Data Index: 1641948 (Python Code)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8641. Min Act: -0.1700
Data Index: 1507501 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8323. Min Act: -0.1700
Data Index: 1379384 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8005. Min Act: -0.1700
Data Index: 1564915 (Python Code)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8164. Min Act: -0.1700
Data Index: 1426249 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8164. Min Act: -0.1700
Data Index: 1533040 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7846. Min Act: -0.1700
Data Index: 1561727 (Python Code)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7846. Min Act: -0.1700
Data Index: 1547664 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8005. Min Act: -0.1700
Data Index: 1601152 (Python Code)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7686. Min Act: -0.1700
Data Index: 1395091 (Python Code)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7846. Min Act: -0.1700
Data Index: 1502560 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7527. Min Act: -0.1700
Data Index: 1457726 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7527. Min Act: -0.1700
Data Index: 1393325 (Python Code)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7367. Min Act: -0.1700
Data Index: 1422304 (Python Code)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7207. Min Act: -0.1700
Data Index: 1361781 (Python Code)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7207. Min Act: -0.1700
Data Index: 1541136 (Python Code)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7207. Min Act: -0.1700
Data Index: 1639159 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7207. Min Act: -0.1700
Data Index: 1439139 (Python Code)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19