Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1036 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.2021. Min Act: -0.1700
Data Index: 874603 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1938. Min Act: -0.1700
Data Index: 105007 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1606. Min Act: -0.1700
Data Index: 1164964 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1606. Min Act: -0.1700
Data Index: 205959 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1523. Min Act: -0.1700
Data Index: 760 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1523. Min Act: -0.1700
Data Index: 250265 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1523. Min Act: -0.1700
Data Index: 623381 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1356. Min Act: -0.1700
Data Index: 1147237 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1356. Min Act: -0.1700
Data Index: 973471 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1273. Min Act: -0.1700
Data Index: 1277221 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1356. Min Act: -0.1700
Data Index: 22937 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1356. Min Act: -0.1700
Data Index: 817586 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1273. Min Act: -0.1700
Data Index: 1024034 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1273. Min Act: -0.1700
Data Index: 40111 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1273. Min Act: -0.1700
Data Index: 974259 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1189. Min Act: -0.1700
Data Index: 448486 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1273. Min Act: -0.1700
Data Index: 389178 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1189. Min Act: -0.1700
Data Index: 84306 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1273. Min Act: -0.1700
Data Index: 137932 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2021. Min Range: -2.2021
Max Act: 2.1189. Min Act: -0.1700
Data Index: 886674 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19