Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2035 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0362. Min Range: -4.0362
Max Act: 4.0050. Min Act: -0.1700
Data Index: 38745 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0362. Min Range: -4.0362
Max Act: 4.0050. Min Act: -0.1700
Data Index: 947044 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0362. Min Range: -4.0362
Max Act: 4.0362. Min Act: -0.1700
Data Index: 389587 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0362. Min Range: -4.0362
Max Act: 4.0050. Min Act: -0.1700
Data Index: 731302 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8173. Min Act: -0.1700
Data Index: 249498 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8799. Min Act: -0.1700
Data Index: 102619 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8799. Min Act: -0.1700
Data Index: 921661 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8486. Min Act: -0.1700
Data Index: 937268 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8173. Min Act: -0.1700
Data Index: 619459 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8173. Min Act: -0.1700
Data Index: 766299 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8173. Min Act: -0.1700
Data Index: 469439 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.7861. Min Act: -0.1700
Data Index: 361275 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.7861. Min Act: -0.1700
Data Index: 621091 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8486. Min Act: -0.1700
Data Index: 760176 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8173. Min Act: -0.1700
Data Index: 576125 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.8486. Min Act: -0.1700
Data Index: 1266805 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.7861. Min Act: -0.1700
Data Index: 1149948 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.7548. Min Act: -0.1700
Data Index: 84057 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.7235. Min Act: -0.1700
Data Index: 82592 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0362. Min Range: -4.0362
Max Act: 3.7548. Min Act: -0.1700
Data Index: 1139169 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19