Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.7056. Min Act: -0.1700
Data Index: 1428485 (Python Code)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.5611. Min Act: -0.1700
Data Index: 1450412 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.5449. Min Act: -0.1700
Data Index: 1454076 (Python Code)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.5288. Min Act: -0.1700
Data Index: 1008023 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.5126. Min Act: -0.1700
Data Index: 1559609 (Python Code)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4964. Min Act: -0.1700
Data Index: 1127190 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4802. Min Act: -0.1700
Data Index: 1557034 (Python Code)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4802. Min Act: -0.1700
Data Index: 1547464 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4802. Min Act: -0.1700
Data Index: 1253926 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4802. Min Act: -0.1700
Data Index: 1432291 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4640. Min Act: -0.1700
Data Index: 1467331 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4640. Min Act: -0.1700
Data Index: 1060696 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4640. Min Act: -0.1700
Data Index: 1256147 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4640. Min Act: -0.1700
Data Index: 791531 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4640. Min Act: -0.1700
Data Index: 63416 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4477. Min Act: -0.1700
Data Index: 575587 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4477. Min Act: -0.1700
Data Index: 1536886 (Python Code)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4315. Min Act: -0.1700
Data Index: 1599004 (Python Code)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4640. Min Act: -0.1700
Data Index: 240119 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7056. Min Range: -2.7056
Max Act: 2.4477. Min Act: -0.1700
Data Index: 755304 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19