Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2006 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.4312. Min Act: -0.1700
Data Index: 1210831 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3823. Min Act: -0.1700
Data Index: 1248175 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3986. Min Act: -0.1700
Data Index: 1481346 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3823. Min Act: -0.1700
Data Index: 1252790 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3659. Min Act: -0.1700
Data Index: 18026 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3659. Min Act: -0.1700
Data Index: 1007378 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3496. Min Act: -0.1700
Data Index: 1654423 (Python Code)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3659. Min Act: -0.1699
Data Index: 1603758 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3659. Min Act: -0.1700
Data Index: 1616763 (Python Code)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3659. Min Act: -0.1700
Data Index: 277798 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3496. Min Act: -0.1700
Data Index: 115639 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3496. Min Act: -0.1700
Data Index: 1649003 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3496. Min Act: -0.1700
Data Index: 1526902 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3496. Min Act: -0.1700
Data Index: 1289594 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3332. Min Act: -0.1700
Data Index: 1273098 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3496. Min Act: -0.1700
Data Index: 950121 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3332. Min Act: -0.1700
Data Index: 464355 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3332. Min Act: -0.1700
Data Index: 180416 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3168. Min Act: -0.1700
Data Index: 1632414 (Python Code)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4312. Min Range: -2.4312
Max Act: 2.3168. Min Act: -0.1700
Data Index: 1402952 (Python Code)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19