Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1169 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0949. Min Range: -3.0949
Max Act: 3.0949. Min Act: -0.1700
Data Index: 1632983 (Python Code)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.9051. Min Act: -0.1700
Data Index: 1217992 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8734. Min Act: -0.1700
Data Index: 1133717 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8734. Min Act: -0.1700
Data Index: 773733 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8575. Min Act: -0.1700
Data Index: 1514935 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8734. Min Act: -0.1700
Data Index: 981881 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8575. Min Act: -0.1700
Data Index: 933652 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8416. Min Act: -0.1700
Data Index: 685632 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8257. Min Act: -0.1700
Data Index: 827676 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8257. Min Act: -0.1700
Data Index: 1559799 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8416. Min Act: -0.1700
Data Index: 1408833 (Python Code)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8257. Min Act: -0.1700
Data Index: 526437 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8098. Min Act: -0.1700
Data Index: 206474 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.7939. Min Act: -0.1700
Data Index: 548481 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.8098. Min Act: -0.1700
Data Index: 1182420 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.7939. Min Act: -0.1700
Data Index: 1180865 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.7779. Min Act: -0.1700
Data Index: 516769 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.7939. Min Act: -0.1700
Data Index: 111666 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.7939. Min Act: -0.1700
Data Index: 649882 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0949. Min Range: -3.0949
Max Act: 2.7939. Min Act: -0.1700
Data Index: 330125 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19