Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1696 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.2084. Min Range: -4.2084
Max Act: 4.2084. Min Act: -0.1700
Data Index: 226418 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2084. Min Range: -4.2084
Max Act: 4.1146. Min Act: -0.1700
Data Index: 641949 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2084. Min Range: -4.2084
Max Act: 4.0834. Min Act: -0.1700
Data Index: 1220466 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9896. Min Act: -0.1700
Data Index: 614586 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9896. Min Act: -0.1700
Data Index: 1199445 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9896. Min Act: -0.1700
Data Index: 1170815 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2084. Min Range: -4.2084
Max Act: 4.0521. Min Act: -0.1700
Data Index: 524763 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9270. Min Act: -0.1700
Data Index: 748495 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9270. Min Act: -0.1700
Data Index: 1537473 (Python Code)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9583. Min Act: -0.1700
Data Index: 856948 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9896. Min Act: -0.1700
Data Index: 710477 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9270. Min Act: -0.1700
Data Index: 941526 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9270. Min Act: -0.1700
Data Index: 863155 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9583. Min Act: -0.1700
Data Index: 1123028 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9270. Min Act: -0.1700
Data Index: 1074712 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9270. Min Act: -0.1700
Data Index: 346618 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.8958. Min Act: -0.1700
Data Index: 135674 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.8645. Min Act: -0.1700
Data Index: 1094399 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.8958. Min Act: -0.1700
Data Index: 710089 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2084. Min Range: -4.2084
Max Act: 3.9270. Min Act: -0.1700
Data Index: 336218 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19