Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1980 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.7595. Min Act: -0.1700
Data Index: 822875 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.7116. Min Act: -0.1700
Data Index: 61162 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.6635. Min Act: -0.1700
Data Index: 406325 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.6314. Min Act: -0.1700
Data Index: 1528219 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.6314. Min Act: -0.1700
Data Index: 269613 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.6475. Min Act: -0.1700
Data Index: 1182782 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.6314. Min Act: -0.1700
Data Index: 1524187 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.6314. Min Act: -0.1700
Data Index: 699970 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5993. Min Act: -0.1700
Data Index: 1519451 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.6154. Min Act: -0.1700
Data Index: 544176 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.6314. Min Act: -0.1700
Data Index: 85060 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5993. Min Act: -0.1700
Data Index: 264471 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5993. Min Act: -0.1700
Data Index: 1438000 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5832. Min Act: -0.1700
Data Index: 1535701 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5832. Min Act: -0.1700
Data Index: 1656133 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5993. Min Act: -0.1700
Data Index: 1242024 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5671. Min Act: -0.1700
Data Index: 1222184 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5671. Min Act: -0.1700
Data Index: 1397870 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5832. Min Act: -0.1700
Data Index: 1529381 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7595. Min Range: -2.7595
Max Act: 2.5993. Min Act: -0.1700
Data Index: 1372526 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19