Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 21 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.2101. Min Act: -0.1700
Data Index: 160728 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.1475. Min Act: -0.1700
Data Index: 1088384 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.1475. Min Act: -0.1700
Data Index: 325217 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.1163. Min Act: -0.1700
Data Index: 830686 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.1163. Min Act: -0.1700
Data Index: 1208805 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.1163. Min Act: -0.1700
Data Index: 1301023 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.1163. Min Act: -0.1700
Data Index: 853646 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0538. Min Act: -0.1700
Data Index: 1030800 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0538. Min Act: -0.1700
Data Index: 546970 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0538. Min Act: -0.1700
Data Index: 1095608 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0225. Min Act: -0.1700
Data Index: 82334 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0538. Min Act: -0.1700
Data Index: 1177392 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0225. Min Act: -0.1700
Data Index: 542225 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0538. Min Act: -0.1700
Data Index: 1323095 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0225. Min Act: -0.1700
Data Index: 1136857 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0225. Min Act: -0.1700
Data Index: 1071437 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0225. Min Act: -0.1700
Data Index: 439527 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2101. Min Range: -4.2101
Max Act: 4.0225. Min Act: -0.1700
Data Index: 97892 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2101. Min Range: -4.2101
Max Act: 3.9912. Min Act: -0.1700
Data Index: 972367 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2101. Min Range: -4.2101
Max Act: 3.9912. Min Act: -0.1700
Data Index: 1167017 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19