Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1960 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.7672. Min Act: -0.1700
Data Index: 323608 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.7353. Min Act: -0.1700
Data Index: 786517 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.7672. Min Act: -0.1700
Data Index: 498361 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.7193. Min Act: -0.1700
Data Index: 110583 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.7033. Min Act: -0.1700
Data Index: 330117 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.6873. Min Act: -0.1700
Data Index: 1131130 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.6713. Min Act: -0.1700
Data Index: 320898 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.6552. Min Act: -0.1700
Data Index: 426329 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.6070. Min Act: -0.1700
Data Index: 833441 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.5909. Min Act: -0.1700
Data Index: 265451 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.6231. Min Act: -0.1700
Data Index: 749535 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.6070. Min Act: -0.1700
Data Index: 391916 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.6070. Min Act: -0.1700
Data Index: 1200172 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.5909. Min Act: -0.1700
Data Index: 530347 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.5909. Min Act: -0.1700
Data Index: 822942 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.5909. Min Act: -0.1700
Data Index: 786159 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.5909. Min Act: -0.1700
Data Index: 779766 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.5909. Min Act: -0.1700
Data Index: 911651 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.5909. Min Act: -0.1700
Data Index: 288772 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7672. Min Range: -2.7672
Max Act: 2.5587. Min Act: -0.1700
Data Index: 632865 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19