Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 497 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.6049. Min Act: -0.1700
Data Index: 288018 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.5109. Min Act: -0.1700
Data Index: 369489 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.4639. Min Act: -0.1700
Data Index: 211234 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.4482. Min Act: -0.1700
Data Index: 884443 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.4482. Min Act: -0.1700
Data Index: 51433 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.4325. Min Act: -0.1700
Data Index: 1160743 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.4325. Min Act: -0.1700
Data Index: 1139186 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.4012. Min Act: -0.1700
Data Index: 970606 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3855. Min Act: -0.1700
Data Index: 120291 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3698. Min Act: -0.1700
Data Index: 733484 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3541. Min Act: -0.1700
Data Index: 726207 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3384. Min Act: -0.1700
Data Index: 875264 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3541. Min Act: -0.1700
Data Index: 1098621 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3541. Min Act: -0.1700
Data Index: 1090141 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3384. Min Act: -0.1700
Data Index: 673718 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3541. Min Act: -0.1700
Data Index: 491207 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3227. Min Act: -0.1700
Data Index: 341294 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3070. Min Act: -0.1700
Data Index: 273529 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.2756. Min Act: -0.1700
Data Index: 302341 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6049. Min Range: -3.6049
Max Act: 3.3384. Min Act: -0.1700
Data Index: 1039128 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19