Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1719 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.5296. Min Act: -0.1700
Data Index: 1127960 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.4323. Min Act: -0.1700
Data Index: 704032 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.4160. Min Act: -0.1700
Data Index: 1622931 (Python Code)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3997. Min Act: -0.1700
Data Index: 1140150 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3997. Min Act: -0.1700
Data Index: 443068 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3834. Min Act: -0.1700
Data Index: 222784 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3834. Min Act: -0.1700
Data Index: 1226291 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3671. Min Act: -0.1700
Data Index: 1071429 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3507. Min Act: -0.1700
Data Index: 198439 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3507. Min Act: -0.1700
Data Index: 315192 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3507. Min Act: -0.1700
Data Index: 1256312 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3507. Min Act: -0.1700
Data Index: 1205493 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3343. Min Act: -0.1700
Data Index: 459553 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3343. Min Act: -0.1700
Data Index: 1462269 (Python Code)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3343. Min Act: -0.1700
Data Index: 371903 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3343. Min Act: -0.1700
Data Index: 804257 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3179. Min Act: -0.1700
Data Index: 1190524 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3343. Min Act: -0.1700
Data Index: 1203864 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3343. Min Act: -0.1700
Data Index: 164953 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5296. Min Range: -2.5296
Max Act: 2.3343. Min Act: -0.1700
Data Index: 1336544 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19