Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 30 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.7580. Min Act: -0.1700
Data Index: 551382 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.6330. Min Act: -0.1700
Data Index: 142398 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.6330. Min Act: -0.1700
Data Index: 914113 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.5705. Min Act: -0.1700
Data Index: 545306 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.4767. Min Act: -0.1700
Data Index: 559342 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.5080. Min Act: -0.1700
Data Index: 520155 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.4455. Min Act: -0.1700
Data Index: 114301 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.3830. Min Act: -0.1700
Data Index: 284546 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.4142. Min Act: -0.1700
Data Index: 364386 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.4455. Min Act: -0.1700
Data Index: 814786 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.3205. Min Act: -0.1700
Data Index: 217621 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.3517. Min Act: -0.1700
Data Index: 1340890 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.3830. Min Act: -0.1700
Data Index: 782607 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.3205. Min Act: -0.1700
Data Index: 996318 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.3830. Min Act: -0.1700
Data Index: 1224278 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.2892. Min Act: -0.1700
Data Index: 1014386 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.3205. Min Act: -0.1700
Data Index: 1327859 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.3517. Min Act: -0.1700
Data Index: 299086 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.2892. Min Act: -0.1700
Data Index: 776923 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7580. Min Range: -4.7580
Max Act: 4.2892. Min Act: -0.1700
Data Index: 45547 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19