Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2004 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5983. Min Act: -0.1700
Data Index: 348735 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5983. Min Act: -0.1700
Data Index: 708787 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5822. Min Act: -0.1700
Data Index: 647210 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5500. Min Act: -0.1700
Data Index: 160920 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5661. Min Act: -0.1700
Data Index: 672736 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5500. Min Act: -0.1700
Data Index: 944367 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5338. Min Act: -0.1700
Data Index: 540340 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5338. Min Act: -0.1700
Data Index: 63803 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5500. Min Act: -0.1700
Data Index: 827276 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5500. Min Act: -0.1700
Data Index: 400956 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5338. Min Act: -0.1700
Data Index: 311349 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5338. Min Act: -0.1700
Data Index: 181251 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5338. Min Act: -0.1699
Data Index: 339116 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5176. Min Act: -0.1699
Data Index: 876726 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5176. Min Act: -0.1700
Data Index: 332875 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5176. Min Act: -0.1700
Data Index: 90473 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5015. Min Act: -0.1700
Data Index: 615691 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5176. Min Act: -0.1700
Data Index: 927104 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5176. Min Act: -0.1700
Data Index: 632156 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5983. Min Range: -2.5983
Max Act: 2.5015. Min Act: -0.1699
Data Index: 559184 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19