Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 365 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.7474. Min Act: -0.1700
Data Index: 544123 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.7474. Min Act: -0.1700
Data Index: 38913 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.7314. Min Act: -0.1700
Data Index: 1317315 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6995. Min Act: -0.1700
Data Index: 362685 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6835. Min Act: -0.1700
Data Index: 81655 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6674. Min Act: -0.1700
Data Index: 278656 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6835. Min Act: -0.1700
Data Index: 930020 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6835. Min Act: -0.1700
Data Index: 248265 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6353. Min Act: -0.1700
Data Index: 1507544 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6353. Min Act: -0.1700
Data Index: 1540668 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6353. Min Act: -0.1700
Data Index: 1559733 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6514. Min Act: -0.1700
Data Index: 1081366 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6514. Min Act: -0.1700
Data Index: 211605 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6514. Min Act: -0.1700
Data Index: 465551 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6514. Min Act: -0.1700
Data Index: 271822 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6353. Min Act: -0.1700
Data Index: 135220 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6193. Min Act: -0.1700
Data Index: 627354 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6353. Min Act: -0.1700
Data Index: 435864 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6193. Min Act: -0.1700
Data Index: 990885 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7474. Min Range: -2.7474
Max Act: 2.6353. Min Act: -0.1700
Data Index: 218817 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19