Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 119 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4958. Min Act: -0.1700
Data Index: 1235911 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4958. Min Act: -0.1700
Data Index: 921134 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4634. Min Act: -0.1700
Data Index: 133201 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4471. Min Act: -0.1700
Data Index: 899158 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4471. Min Act: -0.1700
Data Index: 1021317 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4308. Min Act: -0.1700
Data Index: 1358719 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4146. Min Act: -0.1700
Data Index: 545816 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4308. Min Act: -0.1700
Data Index: 870575 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4308. Min Act: -0.1700
Data Index: 1338277 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4308. Min Act: -0.1700
Data Index: 955178 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4146. Min Act: -0.1700
Data Index: 896675 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4146. Min Act: -0.1700
Data Index: 420456 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.4308. Min Act: -0.1700
Data Index: 3441 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.3819. Min Act: -0.1700
Data Index: 1310063 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.3983. Min Act: -0.1700
Data Index: 1257870 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.3656. Min Act: -0.1700
Data Index: 274685 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.3819. Min Act: -0.1700
Data Index: 1296198 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.3819. Min Act: -0.1700
Data Index: 292674 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.3656. Min Act: -0.1700
Data Index: 878410 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4958. Min Range: -2.4958
Max Act: 2.3819. Min Act: -0.1700
Data Index: 1307601 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19