Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1400 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.9082. Min Act: -0.1700
Data Index: 336889 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.6894. Min Act: -0.1700
Data Index: 1053648 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.5644. Min Act: -0.1700
Data Index: 1027254 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.6582. Min Act: -0.1700
Data Index: 525232 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.5332. Min Act: -0.1700
Data Index: 1159190 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.5332. Min Act: -0.1700
Data Index: 1196441 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.5019. Min Act: -0.1700
Data Index: 408684 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.4707. Min Act: -0.1700
Data Index: 884646 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.5019. Min Act: -0.1700
Data Index: 49706 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.5019. Min Act: -0.1700
Data Index: 1314042 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.5332. Min Act: -0.1700
Data Index: 503035 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.5019. Min Act: -0.1700
Data Index: 8496 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.5019. Min Act: -0.1700
Data Index: 1222383 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.4394. Min Act: -0.1700
Data Index: 224026 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.4081. Min Act: -0.1700
Data Index: 532511 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.4394. Min Act: -0.1700
Data Index: 1015619 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.4707. Min Act: -0.1700
Data Index: 1301235 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.4394. Min Act: -0.1700
Data Index: 694054 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.4081. Min Act: -0.1700
Data Index: 1123864 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9082. Min Range: -4.9082
Max Act: 4.4081. Min Act: -0.1700
Data Index: 681883 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19