Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1899 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 5.0082. Min Range: -5.0082
Max Act: 5.0082. Min Act: -0.1700
Data Index: 249978 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.7894. Min Act: -0.1700
Data Index: 144094 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6332. Min Act: -0.1700
Data Index: 150298 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6332. Min Act: -0.1700
Data Index: 287496 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.5707. Min Act: -0.1700
Data Index: 1006396 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.5707. Min Act: -0.1700
Data Index: 537550 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.5707. Min Act: -0.1700
Data Index: 1162770 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.5707. Min Act: -0.1639
Data Index: 1263085 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.5394. Min Act: -0.1700
Data Index: 1078638 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.5394. Min Act: -0.1700
Data Index: 80131 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.5394. Min Act: -0.1700
Data Index: 113656 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.5394. Min Act: -0.1700
Data Index: 970226 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.5082. Min Act: -0.1700
Data Index: 1182419 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.4769. Min Act: -0.1700
Data Index: 1312346 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.4769. Min Act: -0.1700
Data Index: 1278423 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.4769. Min Act: -0.1700
Data Index: 645253 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.4769. Min Act: -0.1700
Data Index: 210891 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.4457. Min Act: -0.1700
Data Index: 1130798 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.4457. Min Act: -0.1696
Data Index: 1130876 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.4144. Min Act: -0.1700
Data Index: 684846 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19