Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1986 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.8625. Min Act: -0.1700
Data Index: 1513415 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.8307. Min Act: -0.1700
Data Index: 1529173 (Python Code)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.8307. Min Act: -0.1700
Data Index: 1475253 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.8148. Min Act: -0.1700
Data Index: 1414692 (Python Code)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7989. Min Act: -0.1700
Data Index: 1491022 (Python Code)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7989. Min Act: -0.1700
Data Index: 1429440 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7829. Min Act: -0.1700
Data Index: 1448097 (Python Code)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7670. Min Act: -0.1700
Data Index: 1411860 (Python Code)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7670. Min Act: -0.1700
Data Index: 1616943 (Python Code)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7670. Min Act: -0.1700
Data Index: 1424778 (Python Code)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7510. Min Act: -0.1700
Data Index: 1589054 (Python Code)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7510. Min Act: -0.1700
Data Index: 1517891 (Python Code)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7351. Min Act: -0.1700
Data Index: 1405474 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7670. Min Act: -0.1700
Data Index: 1465620 (Python Code)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7510. Min Act: -0.1700
Data Index: 1483632 (Python Code)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7510. Min Act: -0.1700
Data Index: 1459120 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7510. Min Act: -0.1700
Data Index: 1449556 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7510. Min Act: -0.1700
Data Index: 1408566 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7351. Min Act: -0.1700
Data Index: 1457224 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8625. Min Range: -2.8625
Max Act: 2.7510. Min Act: -0.1700
Data Index: 1501113 (Python Code)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19