Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 87 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.4331. Min Act: -0.1700
Data Index: 1372290 (Python Code)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.4331. Min Act: -0.1700
Data Index: 1398109 (Python Code)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.3679. Min Act: -0.1700
Data Index: 1475757 (Python Code)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.3187. Min Act: -0.1700
Data Index: 1637071 (Python Code)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.2858. Min Act: -0.1700
Data Index: 1448665 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.2858. Min Act: -0.1700
Data Index: 1450817 (Python Code)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.2198. Min Act: -0.1700
Data Index: 1404420 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.2198. Min Act: -0.1699
Data Index: 1631557 (Python Code)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.1700. Min Act: -0.1700
Data Index: 1490659 (Python Code)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.1367. Min Act: -0.1700
Data Index: 1475921 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.1200. Min Act: -0.1700
Data Index: 1489775 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.1033. Min Act: -0.1700
Data Index: 1446705 (Python Code)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.0530. Min Act: -0.1700
Data Index: 1649882 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4331. Min Range: -2.4331
Max Act: 2.0530. Min Act: -0.1700
Data Index: 1543680 (Python Code)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4331. Min Range: -2.4331
Max Act: 1.9941. Min Act: -0.1700
Data Index: 1621213 (Python Code)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4331. Min Range: -2.4331
Max Act: 1.9771. Min Act: -0.1700
Data Index: 51044 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4331. Min Range: -2.4331
Max Act: 1.9263. Min Act: -0.1700
Data Index: 1510216 (Python Code)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4331. Min Range: -2.4331
Max Act: 1.8922. Min Act: -0.1700
Data Index: 1510106 (Python Code)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4331. Min Range: -2.4331
Max Act: 1.8238. Min Act: -0.1700
Data Index: 1475372 (Python Code)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4331. Min Range: -2.4331
Max Act: 1.8066. Min Act: -0.1700
Data Index: 1574618 (Python Code)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19