Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 35 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0998. Min Range: -6.0998
Max Act: 6.0998. Min Act: -0.1700
Data Index: 996184 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0998. Min Range: -6.0998
Max Act: 6.0060. Min Act: -0.1700
Data Index: 177691 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.9435. Min Act: -0.1700
Data Index: 1201972 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.7873. Min Act: -0.1700
Data Index: 1033711 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.8498. Min Act: -0.1700
Data Index: 800119 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.8185. Min Act: -0.1700
Data Index: 999028 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.7560. Min Act: -0.1700
Data Index: 962160 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.8185. Min Act: -0.1700
Data Index: 496801 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.6935. Min Act: -0.1700
Data Index: 944849 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.7560. Min Act: -0.1700
Data Index: 283433 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.8185. Min Act: -0.1700
Data Index: 608623 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.6935. Min Act: -0.1700
Data Index: 488015 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.6935. Min Act: -0.1700
Data Index: 1298426 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.7560. Min Act: -0.1700
Data Index: 17968 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.6310. Min Act: -0.1700
Data Index: 963202 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.6310. Min Act: -0.1700
Data Index: 1157973 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.6935. Min Act: -0.1700
Data Index: 1144318 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.7560. Min Act: -0.1700
Data Index: 1067000 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.6310. Min Act: -0.1700
Data Index: 418001 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0998. Min Range: -6.0998
Max Act: 5.7248. Min Act: -0.1700
Data Index: 683754 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19