Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 206 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.2341. Min Act: -0.1700
Data Index: 1506281 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1411283 (Python Code)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.2028. Min Act: -0.1700
Data Index: 1613910 (Python Code)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1434604 (Python Code)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.2028. Min Act: -0.1700
Data Index: 1551327 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.2341. Min Act: -0.1700
Data Index: 1366396 (Python Code)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1395051 (Python Code)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1469391 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1474289 (Python Code)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1422206 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1403. Min Act: -0.1700
Data Index: 1529662 (Python Code)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1435530 (Python Code)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1364008 (Python Code)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1485216 (Python Code)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1477638 (Python Code)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1247. Min Act: -0.1700
Data Index: 1381543 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1403. Min Act: -0.1700
Data Index: 1371948 (Python Code)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1716. Min Act: -0.1700
Data Index: 1376754 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1403. Min Act: -0.1700
Data Index: 1442398 (Python Code)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2341. Min Range: -4.2341
Max Act: 4.1091. Min Act: -0.1700
Data Index: 1465790 (Python Code)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19