Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 646 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.1065. Min Act: -0.1700
Data Index: 526036 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.1065. Min Act: -0.1700
Data Index: 701750 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.1065. Min Act: -0.1700
Data Index: 497635 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0752. Min Act: -0.1700
Data Index: 402094 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0752. Min Act: -0.1700
Data Index: 797615 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0127. Min Act: -0.1700
Data Index: 601110 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0439. Min Act: -0.1700
Data Index: 205102 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0439. Min Act: -0.1700
Data Index: 1101465 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0439. Min Act: -0.1700
Data Index: 1170297 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0439. Min Act: -0.1700
Data Index: 253569 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0439. Min Act: -0.1700
Data Index: 546417 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0439. Min Act: -0.1700
Data Index: 316601 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0439. Min Act: -0.1700
Data Index: 146826 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0127. Min Act: -0.1700
Data Index: 756528 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0127. Min Act: -0.1700
Data Index: 732037 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0127. Min Act: -0.1700
Data Index: 248011 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0127. Min Act: -0.1700
Data Index: 927117 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0127. Min Act: -0.1700
Data Index: 950127 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0127. Min Act: -0.1700
Data Index: 1000260 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1065. Min Range: -4.1065
Max Act: 4.0127. Min Act: -0.1700
Data Index: 588943 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19