Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 107 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.4113. Min Act: -0.1700
Data Index: 407886 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3950. Min Act: -0.1700
Data Index: 868247 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3950. Min Act: -0.1700
Data Index: 373753 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3787. Min Act: -0.1700
Data Index: 272347 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3459. Min Act: -0.1700
Data Index: 829123 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3295. Min Act: -0.1700
Data Index: 97588 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3295. Min Act: -0.1700
Data Index: 1287774 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3295. Min Act: -0.1700
Data Index: 1313488 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3295. Min Act: -0.1700
Data Index: 308147 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3295. Min Act: -0.1700
Data Index: 717947 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3295. Min Act: -0.1700
Data Index: 1276074 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3131. Min Act: -0.1700
Data Index: 992731 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3131. Min Act: -0.1700
Data Index: 223323 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3131. Min Act: -0.1700
Data Index: 1342387 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3131. Min Act: -0.1700
Data Index: 1348900 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3131. Min Act: -0.1700
Data Index: 1149242 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3131. Min Act: -0.1700
Data Index: 1219119 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.3131. Min Act: -0.1700
Data Index: 671041 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.2802. Min Act: -0.1700
Data Index: 2058 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4113. Min Range: -2.4113
Max Act: 2.2967. Min Act: -0.1700
Data Index: 826329 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19