Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 62 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.6242. Min Act: -0.1700
Data Index: 1472316 (Python Code)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5598. Min Act: -0.1700
Data Index: 40135 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1472296 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1617423 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1601133 (Python Code)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5275. Min Act: -0.1700
Data Index: 1519068 (Python Code)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5275. Min Act: -0.1700
Data Index: 1521715 (Python Code)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1528741 (Python Code)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1555867 (Python Code)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5275. Min Act: -0.1700
Data Index: 1590603 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5275. Min Act: -0.1700
Data Index: 1381799 (Python Code)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5275. Min Act: -0.1700
Data Index: 1629834 (Python Code)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1634850 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5275. Min Act: -0.1700
Data Index: 1643340 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1646844 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1465002 (Python Code)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1455494 (Python Code)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1512563 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5275. Min Act: -0.1700
Data Index: 1483825 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6242. Min Range: -2.6242
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1421234 (Python Code)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19