Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1133 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.3241. Min Act: -0.1700
Data Index: 1366528 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.2303. Min Act: -0.1700
Data Index: 1578249 (Python Code)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.2928. Min Act: -0.1700
Data Index: 1641939 (Python Code)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1991. Min Act: -0.1700
Data Index: 1580873 (Python Code)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1678. Min Act: -0.1700
Data Index: 1384830 (Python Code)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1991. Min Act: -0.1700
Data Index: 1459331 (Python Code)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1991. Min Act: -0.1700
Data Index: 1506477 (Python Code)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1991. Min Act: -0.1700
Data Index: 1536607 (Python Code)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1366. Min Act: -0.1700
Data Index: 1480528 (Python Code)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1678. Min Act: -0.1700
Data Index: 1484992 (Python Code)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1678. Min Act: -0.1700
Data Index: 1529524 (Python Code)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1678. Min Act: -0.1700
Data Index: 1141158 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1366. Min Act: -0.1700
Data Index: 1413024 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1519106 (Python Code)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1678. Min Act: -0.1700
Data Index: 1612970 (Python Code)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1459654 (Python Code)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1366. Min Act: -0.1700
Data Index: 1446717 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1544334 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.1366. Min Act: -0.1700
Data Index: 1620045 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3241. Min Range: -4.3241
Max Act: 4.0740. Min Act: -0.1700
Data Index: 1415822 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19