Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 248 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.6608. Min Act: -0.1700
Data Index: 380071 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.6608. Min Act: -0.1700
Data Index: 194313 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.5983. Min Act: -0.1700
Data Index: 1130266 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.5670. Min Act: -0.1700
Data Index: 986634 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.5983. Min Act: -0.1700
Data Index: 145653 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.5983. Min Act: -0.1700
Data Index: 1011009 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.5358. Min Act: -0.1700
Data Index: 466896 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.5983. Min Act: -0.1700
Data Index: 892901 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.5670. Min Act: -0.1700
Data Index: 1092409 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.5358. Min Act: -0.1700
Data Index: 1353264 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.5045. Min Act: -0.1700
Data Index: 810356 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.4420. Min Act: -0.1700
Data Index: 1337548 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.3795. Min Act: -0.1700
Data Index: 1043268 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.4108. Min Act: -0.1700
Data Index: 587947 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.4420. Min Act: -0.1700
Data Index: 1302160 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.4108. Min Act: -0.1700
Data Index: 418996 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.3483. Min Act: -0.1700
Data Index: 926564 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.2858. Min Act: -0.1700
Data Index: 400903 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.3795. Min Act: -0.1700
Data Index: 515034 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6608. Min Range: -4.6608
Max Act: 4.3483. Min Act: -0.1700
Data Index: 429130 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19