Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 185 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.9297. Min Act: -0.1700
Data Index: 1031261 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.9139. Min Act: -0.1700
Data Index: 890367 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.9139. Min Act: -0.1700
Data Index: 460408 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8980. Min Act: -0.1700
Data Index: 97019 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8821. Min Act: -0.1700
Data Index: 541002 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8821. Min Act: -0.1700
Data Index: 1068052 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8663. Min Act: -0.1700
Data Index: 770315 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8345. Min Act: -0.1700
Data Index: 695421 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8345. Min Act: -0.1700
Data Index: 227148 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8186. Min Act: -0.1700
Data Index: 1032872 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8186. Min Act: -0.1700
Data Index: 750856 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8186. Min Act: -0.1700
Data Index: 164572 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.8027. Min Act: -0.1700
Data Index: 445591 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.7867. Min Act: -0.1700
Data Index: 357773 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.7867. Min Act: -0.1700
Data Index: 182197 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.7708. Min Act: -0.1700
Data Index: 263933 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.7867. Min Act: -0.1700
Data Index: 834170 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.7708. Min Act: -0.1700
Data Index: 695417 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.7548. Min Act: -0.1700
Data Index: 980654 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9297. Min Range: -2.9297
Max Act: 2.7708. Min Act: -0.1700
Data Index: 201106 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19