Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1925 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4976. Min Act: -0.1700
Data Index: 414216 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4652. Min Act: -0.1700
Data Index: 761891 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4326. Min Act: -0.1700
Data Index: 462682 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4164. Min Act: -0.1700
Data Index: 841682 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3837. Min Act: -0.1699
Data Index: 1414621 (Python Code)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4001. Min Act: -0.1700
Data Index: 1390045 (Python Code)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4001. Min Act: -0.1700
Data Index: 1410118 (Python Code)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4001. Min Act: -0.1700
Data Index: 1639464 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4001. Min Act: -0.1700
Data Index: 896723 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3837. Min Act: -0.1700
Data Index: 185938 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4001. Min Act: -0.1700
Data Index: 458415 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3837. Min Act: -0.1700
Data Index: 489614 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3674. Min Act: -0.1699
Data Index: 1589702 (Python Code)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3837. Min Act: -0.1700
Data Index: 1416898 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3837. Min Act: -0.1699
Data Index: 1567957 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3837. Min Act: -0.1700
Data Index: 1643353 (Python Code)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3674. Min Act: -0.1700
Data Index: 1298928 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.4001. Min Act: -0.1700
Data Index: 151078 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3837. Min Act: -0.1700
Data Index: 186057 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4976. Min Range: -2.4976
Max Act: 2.3674. Min Act: -0.1700
Data Index: 1645909 (Python Code)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19