Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2034 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.7691. Min Act: -0.1700
Data Index: 1112380 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.7052. Min Act: -0.1700
Data Index: 184315 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.6732. Min Act: -0.1700
Data Index: 574988 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.6411. Min Act: -0.1700
Data Index: 1283555 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.6251. Min Act: -0.1700
Data Index: 662361 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.6251. Min Act: -0.1700
Data Index: 288379 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.6251. Min Act: -0.1700
Data Index: 795406 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.6090. Min Act: -0.1700
Data Index: 1270861 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.6090. Min Act: -0.1700
Data Index: 1271426 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.6090. Min Act: -0.1700
Data Index: 812377 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.6090. Min Act: -0.1700
Data Index: 1020010 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.5929. Min Act: -0.1700
Data Index: 1265556 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.5929. Min Act: -0.1700
Data Index: 635139 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.5768. Min Act: -0.1700
Data Index: 116061 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.5607. Min Act: -0.1700
Data Index: 126980 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.5607. Min Act: -0.1700
Data Index: 1185365 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.5607. Min Act: -0.1700
Data Index: 294756 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.5607. Min Act: -0.1700
Data Index: 748080 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.5607. Min Act: -0.1700
Data Index: 896628 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7691. Min Range: -2.7691
Max Act: 2.5445. Min Act: -0.1700
Data Index: 375859 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19