Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 289 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.9042. Min Act: -0.1700
Data Index: 345744 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8883. Min Act: -0.1700
Data Index: 930546 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8725. Min Act: -0.1700
Data Index: 1018748 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8725. Min Act: -0.1700
Data Index: 140394 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8725. Min Act: -0.1700
Data Index: 935175 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8566. Min Act: -0.1700
Data Index: 407288 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8566. Min Act: -0.1700
Data Index: 387839 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8248. Min Act: -0.1700
Data Index: 1302311 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8248. Min Act: -0.1700
Data Index: 634238 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8407. Min Act: -0.1700
Data Index: 874488 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8248. Min Act: -0.1700
Data Index: 1274350 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8407. Min Act: -0.1700
Data Index: 1219706 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8407. Min Act: -0.1700
Data Index: 463276 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8248. Min Act: -0.1700
Data Index: 1318473 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8248. Min Act: -0.1700
Data Index: 1173615 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8089. Min Act: -0.1700
Data Index: 1117947 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.7929. Min Act: -0.1700
Data Index: 260770 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8089. Min Act: -0.1700
Data Index: 254846 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.8089. Min Act: -0.1700
Data Index: 953409 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9042. Min Range: -2.9042
Max Act: 2.7929. Min Act: -0.1700
Data Index: 985976 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19