Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 116 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0194. Min Range: -3.0194
Max Act: 3.0194. Min Act: -0.1700
Data Index: 50806 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.9561. Min Act: -0.1700
Data Index: 93501 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.9086. Min Act: -0.1700
Data Index: 647505 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.9086. Min Act: -0.1700
Data Index: 1185716 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8928. Min Act: -0.1700
Data Index: 659758 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8769. Min Act: -0.1700
Data Index: 646802 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8610. Min Act: -0.1700
Data Index: 230261 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8292. Min Act: -0.1700
Data Index: 134787 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8292. Min Act: -0.1700
Data Index: 755625 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8292. Min Act: -0.1700
Data Index: 474401 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8292. Min Act: -0.1700
Data Index: 999685 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8292. Min Act: -0.1700
Data Index: 236376 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8292. Min Act: -0.1700
Data Index: 1065633 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8133. Min Act: -0.1700
Data Index: 1157574 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8133. Min Act: -0.1700
Data Index: 771461 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8292. Min Act: -0.1700
Data Index: 669790 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.8133. Min Act: -0.1700
Data Index: 290082 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.7814. Min Act: -0.1700
Data Index: 644670 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.7974. Min Act: -0.1700
Data Index: 316290 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0194. Min Range: -3.0194
Max Act: 2.7974. Min Act: -0.1700
Data Index: 70990 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19