Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1408 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.4007. Min Act: -0.1700
Data Index: 430668 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.2444. Min Act: -0.1700
Data Index: 656643 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.2444. Min Act: -0.1700
Data Index: 1256132 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.1819. Min Act: -0.1700
Data Index: 908377 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.1819. Min Act: -0.1700
Data Index: 706255 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.1819. Min Act: -0.1700
Data Index: 1107279 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.1506. Min Act: -0.1700
Data Index: 891320 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.1193. Min Act: -0.1700
Data Index: 917998 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.0881. Min Act: -0.1700
Data Index: 399553 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.0881. Min Act: -0.1700
Data Index: 971629 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.1193. Min Act: -0.1700
Data Index: 479691 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.0881. Min Act: -0.1700
Data Index: 345060 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.0568. Min Act: -0.1700
Data Index: 1128713 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.0568. Min Act: -0.1700
Data Index: 541543 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4007. Min Range: -4.4007
Max Act: 3.9943. Min Act: -0.1700
Data Index: 38869 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.0256. Min Act: -0.1700
Data Index: 1259091 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4007. Min Range: -4.4007
Max Act: 4.0256. Min Act: -0.1700
Data Index: 997868 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4007. Min Range: -4.4007
Max Act: 3.9943. Min Act: -0.1700
Data Index: 145628 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4007. Min Range: -4.4007
Max Act: 3.9943. Min Act: -0.1700
Data Index: 262503 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4007. Min Range: -4.4007
Max Act: 3.9943. Min Act: -0.1700
Data Index: 1068602 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19