Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2000 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.6703. Min Act: -0.1700
Data Index: 1476503 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.6382. Min Act: -0.1700
Data Index: 1360445 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.6703. Min Act: -0.1700
Data Index: 1587421 (Python Code)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.6060. Min Act: -0.1700
Data Index: 1529337 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.6221. Min Act: -0.1700
Data Index: 1625309 (Python Code)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.6060. Min Act: -0.1700
Data Index: 1464224 (Python Code)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.6060. Min Act: -0.1700
Data Index: 1478029 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.6060. Min Act: -0.1700
Data Index: 1366776 (Python Code)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5900. Min Act: -0.1700
Data Index: 1627399 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5900. Min Act: -0.1700
Data Index: 1638263 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5738. Min Act: -0.1700
Data Index: 1588325 (Python Code)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5900. Min Act: -0.1700
Data Index: 1581956 (Python Code)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5900. Min Act: -0.1700
Data Index: 1463094 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5738. Min Act: -0.1700
Data Index: 1561388 (Python Code)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5900. Min Act: -0.1700
Data Index: 1623782 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5900. Min Act: -0.1700
Data Index: 1526720 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5900. Min Act: -0.1700
Data Index: 1635281 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5900. Min Act: -0.1700
Data Index: 1443747 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.6060. Min Act: -0.1700
Data Index: 1389659 (Python Code)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6703. Min Range: -2.6703
Max Act: 2.5738. Min Act: -0.1700
Data Index: 1491475 (Python Code)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19