Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1940 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.4552. Min Act: -0.1700
Data Index: 62705 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.4552. Min Act: -0.1700
Data Index: 909805 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.3302. Min Act: -0.1700
Data Index: 7788 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.2989. Min Act: -0.1700
Data Index: 286705 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.1739. Min Act: -0.1700
Data Index: 625495 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.2052. Min Act: -0.1700
Data Index: 497037 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.1427. Min Act: -0.1700
Data Index: 672878 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.2052. Min Act: -0.1700
Data Index: 969102 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.2364. Min Act: -0.1700
Data Index: 348880 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.1739. Min Act: -0.1700
Data Index: 919830 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.2677. Min Act: -0.1700
Data Index: 918673 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.1739. Min Act: -0.1700
Data Index: 22030 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.1427. Min Act: -0.1700
Data Index: 431581 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.1427. Min Act: -0.1700
Data Index: 725932 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.1427. Min Act: -0.1700
Data Index: 309962 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.0801. Min Act: -0.1700
Data Index: 1341676 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.1114. Min Act: -0.1700
Data Index: 282117 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.0801. Min Act: -0.1700
Data Index: 306842 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.0489. Min Act: -0.1700
Data Index: 271768 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4552. Min Range: -4.4552
Max Act: 4.0801. Min Act: -0.1700
Data Index: 423700 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19