Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1070 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2421. Min Act: -0.1700
Data Index: 1613994 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.3046. Min Act: -0.1700
Data Index: 1503970 (Python Code)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2421. Min Act: -0.1700
Data Index: 1645168 (Python Code)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2733. Min Act: -0.1700
Data Index: 1592256 (Python Code)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2733. Min Act: -0.1700
Data Index: 1528710 (Python Code)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2733. Min Act: -0.1700
Data Index: 1655826 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2733. Min Act: -0.1700
Data Index: 1415698 (Python Code)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2421. Min Act: -0.1700
Data Index: 1598111 (Python Code)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2421. Min Act: -0.1700
Data Index: 1455603 (Python Code)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2108. Min Act: -0.1700
Data Index: 1443528 (Python Code)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2421. Min Act: -0.1700
Data Index: 1516353 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2108. Min Act: -0.1700
Data Index: 1398300 (Python Code)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2421. Min Act: -0.1700
Data Index: 1520904 (Python Code)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.1795. Min Act: -0.1700
Data Index: 1494356 (Python Code)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2108. Min Act: -0.1700
Data Index: 1595685 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2108. Min Act: -0.1700
Data Index: 1394417 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.2108. Min Act: -0.1700
Data Index: 1477514 (Python Code)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.1483. Min Act: -0.1700
Data Index: 1501450 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.1170. Min Act: -0.1700
Data Index: 1431761 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3046. Min Range: -4.3046
Max Act: 4.1483. Min Act: -0.1700
Data Index: 1573095 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19