Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 70 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0438. Min Range: -3.0438
Max Act: 3.0438. Min Act: -0.1700
Data Index: 831053 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.7901. Min Act: -0.1700
Data Index: 265203 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.8061. Min Act: -0.1700
Data Index: 1230952 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.8220. Min Act: -0.1700
Data Index: 1236972 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.8061. Min Act: -0.1700
Data Index: 358956 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.7263. Min Act: -0.1700
Data Index: 1353753 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.7742. Min Act: -0.1700
Data Index: 1266380 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.7263. Min Act: -0.1700
Data Index: 679214 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.7103. Min Act: -0.1700
Data Index: 398147 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.7103. Min Act: -0.1700
Data Index: 97844 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.7103. Min Act: -0.1700
Data Index: 1313395 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.6783. Min Act: -0.1700
Data Index: 521392 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.6783. Min Act: -0.1700
Data Index: 393559 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.6943. Min Act: -0.1700
Data Index: 824182 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.6943. Min Act: -0.1700
Data Index: 910529 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.6623. Min Act: -0.1700
Data Index: 1192942 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.6783. Min Act: -0.1700
Data Index: 814465 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.6783. Min Act: -0.1700
Data Index: 143477 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.6783. Min Act: -0.1700
Data Index: 898474 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0438. Min Range: -3.0438
Max Act: 2.6623. Min Act: -0.1700
Data Index: 1053659 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19