Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 256 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.5921. Min Act: -0.1700
Data Index: 76488 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.5760. Min Act: -0.1700
Data Index: 1315376 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.5114. Min Act: -0.1700
Data Index: 1305791 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4952. Min Act: -0.1700
Data Index: 1142104 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.5114. Min Act: -0.1700
Data Index: 662196 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4952. Min Act: -0.1700
Data Index: 1352550 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4790. Min Act: -0.1700
Data Index: 938962 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4465. Min Act: -0.1700
Data Index: 165702 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4628. Min Act: -0.1700
Data Index: 103786 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4465. Min Act: -0.1700
Data Index: 1030606 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4465. Min Act: -0.1700
Data Index: 1362421 (Python Code)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4303. Min Act: -0.1700
Data Index: 1232915 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4465. Min Act: -0.1700
Data Index: 350808 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4465. Min Act: -0.1700
Data Index: 1286697 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4303. Min Act: -0.1700
Data Index: 436392 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4303. Min Act: -0.1700
Data Index: 582808 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4303. Min Act: -0.1700
Data Index: 924831 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4140. Min Act: -0.1700
Data Index: 191593 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4140. Min Act: -0.1700
Data Index: 1306196 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5921. Min Range: -2.5921
Max Act: 2.4140. Min Act: -0.1700
Data Index: 365382 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19