Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 206 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.9605. Min Act: -0.1698
Data Index: 1553162 (Python Code)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8654. Min Act: -0.1700
Data Index: 865389 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8495. Min Act: -0.1700
Data Index: 934857 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8495. Min Act: -0.1700
Data Index: 1277089 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8495. Min Act: -0.1700
Data Index: 111375 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8495. Min Act: -0.1700
Data Index: 505070 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8018. Min Act: -0.1700
Data Index: 604829 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8177. Min Act: -0.1700
Data Index: 186666 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8177. Min Act: -0.1700
Data Index: 318271 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8018. Min Act: -0.1700
Data Index: 1213103 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8018. Min Act: -0.1700
Data Index: 381459 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8018. Min Act: -0.1700
Data Index: 656326 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8177. Min Act: -0.1700
Data Index: 800064 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8018. Min Act: -0.1700
Data Index: 216179 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8177. Min Act: -0.1700
Data Index: 1301969 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8018. Min Act: -0.1700
Data Index: 1121470 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8018. Min Act: -0.1700
Data Index: 1067613 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.7859. Min Act: -0.1700
Data Index: 645253 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.8018. Min Act: -0.1700
Data Index: 1063430 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9605. Min Range: -2.9605
Max Act: 2.7859. Min Act: -0.1700
Data Index: 290959 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19