Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 767 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.2704. Min Act: -0.1700
Data Index: 516651 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.3019. Min Act: -0.1700
Data Index: 1160812 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.2547. Min Act: -0.1700
Data Index: 988242 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1761. Min Act: -0.1700
Data Index: 434145 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.3176. Min Act: -0.1700
Data Index: 273923 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.2233. Min Act: -0.1700
Data Index: 1176375 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1918. Min Act: -0.1700
Data Index: 624304 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1761. Min Act: -0.1700
Data Index: 115341 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1918. Min Act: -0.1700
Data Index: 3501 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1761. Min Act: -0.1700
Data Index: 1341694 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1918. Min Act: -0.1700
Data Index: 1006678 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1131. Min Act: -0.1700
Data Index: 205595 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1761. Min Act: -0.1700
Data Index: 739116 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1918. Min Act: -0.1700
Data Index: 223060 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1446. Min Act: -0.1700
Data Index: 158070 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1761. Min Act: -0.1700
Data Index: 607798 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.0973. Min Act: -0.1700
Data Index: 176065 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1603. Min Act: -0.1700
Data Index: 496813 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1288. Min Act: -0.1700
Data Index: 387142 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3176. Min Range: -3.3176
Max Act: 3.1918. Min Act: -0.1700
Data Index: 897453 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19