Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 265 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.9883. Min Act: -0.1700
Data Index: 1313935 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.9567. Min Act: -0.1700
Data Index: 1037441 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.8456. Min Act: -0.1700
Data Index: 1252438 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.8456. Min Act: -0.1700
Data Index: 1332275 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.8615. Min Act: -0.1700
Data Index: 1320900 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7979. Min Act: -0.1700
Data Index: 624529 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.8138. Min Act: -0.1700
Data Index: 285129 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.8138. Min Act: -0.1700
Data Index: 424729 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7979. Min Act: -0.1700
Data Index: 1211286 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7979. Min Act: -0.1700
Data Index: 415869 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7979. Min Act: -0.1700
Data Index: 1256254 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7820. Min Act: -0.1700
Data Index: 315181 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7660. Min Act: -0.1700
Data Index: 447569 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7979. Min Act: -0.1700
Data Index: 1113886 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7820. Min Act: -0.1700
Data Index: 625546 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7820. Min Act: -0.1700
Data Index: 785107 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7660. Min Act: -0.1700
Data Index: 1175673 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7660. Min Act: -0.1700
Data Index: 439021 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7820. Min Act: -0.1700
Data Index: 987315 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9883. Min Range: -2.9883
Max Act: 2.7820. Min Act: -0.1700
Data Index: 112934 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19