Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 57 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.5756. Min Act: -0.1700
Data Index: 480307 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.4786. Min Act: -0.1700
Data Index: 1259036 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.4624. Min Act: -0.1700
Data Index: 418090 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.4462. Min Act: -0.1700
Data Index: 807839 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.4462. Min Act: -0.1700
Data Index: 625359 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.4136. Min Act: -0.1700
Data Index: 36323 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.4136. Min Act: -0.1700
Data Index: 971129 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.4136. Min Act: -0.1700
Data Index: 887220 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3810. Min Act: -0.1699
Data Index: 318820 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3973. Min Act: -0.1700
Data Index: 781460 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3810. Min Act: -0.1700
Data Index: 1353788 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3973. Min Act: -0.1700
Data Index: 780545 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3646. Min Act: -0.1700
Data Index: 1015156 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3646. Min Act: -0.1700
Data Index: 970535 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3646. Min Act: -0.1700
Data Index: 680562 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3646. Min Act: -0.1700
Data Index: 188062 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3646. Min Act: -0.1700
Data Index: 763441 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3646. Min Act: -0.1700
Data Index: 975827 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3483. Min Act: -0.1700
Data Index: 882693 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5756. Min Range: -2.5756
Max Act: 2.3319. Min Act: -0.1700
Data Index: 420634 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19