Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 781 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.4382. Min Act: -0.1700
Data Index: 1471960 (Python Code)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.4694. Min Act: -0.1700
Data Index: 1522344 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.4694. Min Act: -0.1700
Data Index: 1528700 (Python Code)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.3132. Min Act: -0.1700
Data Index: 1422269 (Python Code)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.3444. Min Act: -0.1700
Data Index: 1364448 (Python Code)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.3444. Min Act: -0.1699
Data Index: 1532287 (Python Code)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.3132. Min Act: -0.1700
Data Index: 1375832 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.3132. Min Act: -0.1700
Data Index: 1429603 (Python Code)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2819. Min Act: -0.1700
Data Index: 418663 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2507. Min Act: -0.1700
Data Index: 1430525 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2507. Min Act: -0.1700
Data Index: 38760 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2194. Min Act: -0.1700
Data Index: 273057 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2819. Min Act: -0.1700
Data Index: 1087156 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2819. Min Act: -0.1700
Data Index: 1528438 (Python Code)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2507. Min Act: -0.1700
Data Index: 1298582 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.1882. Min Act: -0.1700
Data Index: 461517 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.1882. Min Act: -0.1700
Data Index: 1268834 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2194. Min Act: -0.1700
Data Index: 1384855 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2507. Min Act: -0.1699
Data Index: 1601772 (Python Code)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4694. Min Range: -4.4694
Max Act: 4.2194. Min Act: -0.1700
Data Index: 1553103 (Python Code)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19