Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 310 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0838. Min Range: -3.0838
Max Act: 3.0838. Min Act: -0.1700
Data Index: 848106 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9891. Min Act: -0.1700
Data Index: 637413 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0838. Min Range: -3.0838
Max Act: 3.0207. Min Act: -0.1700
Data Index: 1261916 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9733. Min Act: -0.1700
Data Index: 1187083 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9574. Min Act: -0.1700
Data Index: 173839 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9733. Min Act: -0.1700
Data Index: 285959 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9574. Min Act: -0.1700
Data Index: 204497 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9574. Min Act: -0.1700
Data Index: 253591 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9574. Min Act: -0.1700
Data Index: 165022 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9416. Min Act: -0.1700
Data Index: 500637 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9257. Min Act: -0.1700
Data Index: 1211598 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9257. Min Act: -0.1700
Data Index: 669988 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9099. Min Act: -0.1700
Data Index: 989654 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9257. Min Act: -0.1700
Data Index: 1095487 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9257. Min Act: -0.1700
Data Index: 21031 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.8782. Min Act: -0.1700
Data Index: 460517 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9257. Min Act: -0.1700
Data Index: 510183 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9099. Min Act: -0.1700
Data Index: 1038622 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9257. Min Act: -0.1700
Data Index: 618467 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0838. Min Range: -3.0838
Max Act: 2.9099. Min Act: -0.1700
Data Index: 446963 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19