Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 522 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.2197. Min Act: -0.1700
Data Index: 102483 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.1260. Min Act: -0.1700
Data Index: 46397 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.1260. Min Act: -0.1700
Data Index: 231922 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0947. Min Act: -0.1700
Data Index: 947722 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0947. Min Act: -0.1700
Data Index: 1110068 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0322. Min Act: -0.1700
Data Index: 1331132 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0947. Min Act: -0.1700
Data Index: 230343 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0634. Min Act: -0.1700
Data Index: 1074630 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0322. Min Act: -0.1700
Data Index: 828325 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0322. Min Act: -0.1700
Data Index: 673416 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0322. Min Act: -0.1700
Data Index: 788448 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0009. Min Act: -0.1700
Data Index: 1821 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0009. Min Act: -0.1700
Data Index: 454497 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0009. Min Act: -0.1700
Data Index: 282310 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0009. Min Act: -0.1700
Data Index: 636927 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0009. Min Act: -0.1700
Data Index: 1012430 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2197. Min Range: -4.2197
Max Act: 3.9697. Min Act: -0.1700
Data Index: 292413 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2197. Min Range: -4.2197
Max Act: 3.9697. Min Act: -0.1700
Data Index: 137051 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2197. Min Range: -4.2197
Max Act: 3.9697. Min Act: -0.1700
Data Index: 699320 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2197. Min Range: -4.2197
Max Act: 4.0009. Min Act: -0.1700
Data Index: 1196273 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19