Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1183 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.8107. Min Act: -0.1700
Data Index: 453000 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.7150. Min Act: -0.1700
Data Index: 403521 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6509. Min Act: -0.1700
Data Index: 755735 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6349. Min Act: -0.1700
Data Index: 1509354 (Python Code)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6188. Min Act: -0.1699
Data Index: 1544078 (Python Code)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6188. Min Act: -0.1700
Data Index: 1477305 (Python Code)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6188. Min Act: -0.1700
Data Index: 246282 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6188. Min Act: -0.1700
Data Index: 246701 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6188. Min Act: -0.1700
Data Index: 1428115 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6027. Min Act: -0.1700
Data Index: 1485765 (Python Code)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6027. Min Act: -0.1700
Data Index: 246837 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6027. Min Act: -0.1700
Data Index: 156670 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6027. Min Act: -0.1700
Data Index: 432290 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6027. Min Act: -0.1700
Data Index: 1211514 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6027. Min Act: -0.1700
Data Index: 1619601 (Python Code)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.5866. Min Act: -0.1700
Data Index: 1470869 (Python Code)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6027. Min Act: -0.1700
Data Index: 1394224 (Python Code)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6188. Min Act: -0.1700
Data Index: 686978 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.5866. Min Act: -0.1700
Data Index: 464266 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8107. Min Range: -2.8107
Max Act: 2.6027. Min Act: -0.1700
Data Index: 656695 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19