Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1969 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0487. Min Range: -3.0487
Max Act: 3.0487. Min Act: -0.1700
Data Index: 697076 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0487. Min Range: -3.0487
Max Act: 3.0171. Min Act: -0.1700
Data Index: 642415 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0487. Min Range: -3.0487
Max Act: 3.0171. Min Act: -0.1700
Data Index: 1283257 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0487. Min Range: -3.0487
Max Act: 3.0171. Min Act: -0.1700
Data Index: 601256 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0487. Min Range: -3.0487
Max Act: 3.0013. Min Act: -0.1700
Data Index: 493945 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0487. Min Range: -3.0487
Max Act: 3.0171. Min Act: -0.1700
Data Index: 598945 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9855. Min Act: -0.1700
Data Index: 717488 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9855. Min Act: -0.1700
Data Index: 888171 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9855. Min Act: -0.1700
Data Index: 277762 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9697. Min Act: -0.1700
Data Index: 466866 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9697. Min Act: -0.1700
Data Index: 549054 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9697. Min Act: -0.1700
Data Index: 1153985 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9697. Min Act: -0.1700
Data Index: 83683 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9697. Min Act: -0.1700
Data Index: 620207 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9538. Min Act: -0.1700
Data Index: 347926 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9538. Min Act: -0.1700
Data Index: 343965 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9380. Min Act: -0.1700
Data Index: 680409 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9380. Min Act: -0.1700
Data Index: 170281 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9221. Min Act: -0.1700
Data Index: 281924 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0487. Min Range: -3.0487
Max Act: 2.9221. Min Act: -0.1700
Data Index: 460734 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19