Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1472 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.7397. Min Act: -0.1700
Data Index: 1647173 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.4897. Min Act: -0.1700
Data Index: 1637481 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.4584. Min Act: -0.1700
Data Index: 1572802 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.4272. Min Act: -0.1700
Data Index: 1541801 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3647. Min Act: -0.1700
Data Index: 1518406 (Python Code)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3959. Min Act: -0.1700
Data Index: 1646941 (Python Code)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3647. Min Act: -0.1700
Data Index: 1408173 (Python Code)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1624391 (Python Code)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1534984 (Python Code)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1525310 (Python Code)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3959. Min Act: -0.1700
Data Index: 1570230 (Python Code)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3022. Min Act: -0.1700
Data Index: 1465513 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3959. Min Act: -0.1700
Data Index: 1554057 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3022. Min Act: -0.1700
Data Index: 1585045 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3022. Min Act: -0.1700
Data Index: 1610744 (Python Code)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.2709. Min Act: -0.1700
Data Index: 1376373 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3022. Min Act: -0.1700
Data Index: 1621933 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3022. Min Act: -0.1700
Data Index: 1436618 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1614322 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7397. Min Range: -6.7397
Max Act: 6.3647. Min Act: -0.1700
Data Index: 1431519 (Python Code)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19