Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 197 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.9984. Min Act: -0.1700
Data Index: 486905 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.9668. Min Act: -0.1700
Data Index: 1080283 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.9509. Min Act: -0.1700
Data Index: 933094 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.9509. Min Act: -0.1700
Data Index: 850694 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.9193. Min Act: -0.1700
Data Index: 961205 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.9034. Min Act: -0.1700
Data Index: 1289415 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.9034. Min Act: -0.1700
Data Index: 1136219 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8875. Min Act: -0.1700
Data Index: 131465 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8717. Min Act: -0.1700
Data Index: 328711 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8717. Min Act: -0.1700
Data Index: 639445 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8717. Min Act: -0.1700
Data Index: 202192 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8717. Min Act: -0.1700
Data Index: 1227147 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8399. Min Act: -0.1700
Data Index: 736624 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8240. Min Act: -0.1700
Data Index: 824256 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8081. Min Act: -0.1700
Data Index: 1212680 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8399. Min Act: -0.1700
Data Index: 1259870 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8240. Min Act: -0.1700
Data Index: 977728 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8399. Min Act: -0.1700
Data Index: 685625 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8240. Min Act: -0.1700
Data Index: 929310 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.8240. Min Act: -0.1700
Data Index: 1297642 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19