Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1916 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.3318. Min Act: -0.1700
Data Index: 1398692 (Python Code)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.1443. Min Act: -0.1700
Data Index: 1502384 (Python Code)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.1443. Min Act: -0.1700
Data Index: 1424868 (Python Code)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.1443. Min Act: -0.1700
Data Index: 1556285 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.0818. Min Act: -0.1700
Data Index: 1382881 (Python Code)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.0505. Min Act: -0.1700
Data Index: 1654590 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.0818. Min Act: -0.1700
Data Index: 1516484 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.0192. Min Act: -0.1700
Data Index: 1633341 (Python Code)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.0818. Min Act: -0.1700
Data Index: 1550279 (Python Code)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.0192. Min Act: -0.1700
Data Index: 1562219 (Python Code)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.0505. Min Act: -0.1700
Data Index: 1594240 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.0192. Min Act: -0.1700
Data Index: 1562109 (Python Code)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3318. Min Range: -4.3318
Max Act: 3.9880. Min Act: -0.1700
Data Index: 1537801 (Python Code)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3318. Min Range: -4.3318
Max Act: 3.9880. Min Act: -0.1700
Data Index: 1513701 (Python Code)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3318. Min Range: -4.3318
Max Act: 4.0192. Min Act: -0.1700
Data Index: 1469601 (Python Code)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3318. Min Range: -4.3318
Max Act: 3.9880. Min Act: -0.1700
Data Index: 1513749 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3318. Min Range: -4.3318
Max Act: 3.9880. Min Act: -0.1700
Data Index: 1478903 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3318. Min Range: -4.3318
Max Act: 3.9567. Min Act: -0.1700
Data Index: 1555295 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3318. Min Range: -4.3318
Max Act: 3.9254. Min Act: -0.1700
Data Index: 1395718 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3318. Min Range: -4.3318
Max Act: 3.9254. Min Act: -0.1700
Data Index: 1614945 (Python Code)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19