Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1002 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.5650. Min Act: -0.1700
Data Index: 683366 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.4354. Min Act: -0.1700
Data Index: 302060 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.4517. Min Act: -0.1700
Data Index: 601487 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.4028. Min Act: -0.1700
Data Index: 391954 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3865. Min Act: -0.1700
Data Index: 294899 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3865. Min Act: -0.1700
Data Index: 903360 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3702. Min Act: -0.1700
Data Index: 375980 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3702. Min Act: -0.1700
Data Index: 1237200 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3702. Min Act: -0.1700
Data Index: 1343361 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3702. Min Act: -0.1700
Data Index: 630699 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3538. Min Act: -0.1700
Data Index: 900091 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3702. Min Act: -0.1700
Data Index: 611403 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3538. Min Act: -0.1700
Data Index: 68314 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3538. Min Act: -0.1700
Data Index: 1336359 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3210. Min Act: -0.1700
Data Index: 999085 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3210. Min Act: -0.1700
Data Index: 1184362 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3210. Min Act: -0.1700
Data Index: 845586 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3046. Min Act: -0.1700
Data Index: 1218225 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3210. Min Act: -0.1700
Data Index: 681539 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5650. Min Range: -2.5650
Max Act: 2.3210. Min Act: -0.1700
Data Index: 775432 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19