Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 692 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.7900. Min Act: -0.1700
Data Index: 1551858 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.6942. Min Act: -0.1700
Data Index: 1576162 (Python Code)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.6621. Min Act: -0.1700
Data Index: 1415046 (Python Code)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.6300. Min Act: -0.1700
Data Index: 1475221 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.6139. Min Act: -0.1700
Data Index: 1632993 (Python Code)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5495. Min Act: -0.1700
Data Index: 1639060 (Python Code)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5333. Min Act: -0.1700
Data Index: 1386215 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5172. Min Act: -0.1700
Data Index: 1612399 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5172. Min Act: -0.1700
Data Index: 1466367 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5010. Min Act: -0.1700
Data Index: 1640423 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5172. Min Act: -0.1700
Data Index: 1405818 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5333. Min Act: -0.1700
Data Index: 1420089 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5172. Min Act: -0.1700
Data Index: 1183185 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.4848. Min Act: -0.1699
Data Index: 1531107 (Python Code)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5010. Min Act: -0.1700
Data Index: 1585371 (Python Code)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5010. Min Act: -0.1700
Data Index: 1626350 (Python Code)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.5010. Min Act: -0.1700
Data Index: 1476322 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.4848. Min Act: -0.1700
Data Index: 1439395 (Python Code)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.4686. Min Act: -0.1700
Data Index: 1584788 (Python Code)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7900. Min Range: -2.7900
Max Act: 2.4686. Min Act: -0.1700
Data Index: 1622681 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19