Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 200 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.4009. Min Act: -0.1700
Data Index: 121793 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3519. Min Act: -0.1700
Data Index: 524423 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3682. Min Act: -0.1700
Data Index: 1260973 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3519. Min Act: -0.1700
Data Index: 211976 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3355. Min Act: -0.1700
Data Index: 1101367 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3027. Min Act: -0.1700
Data Index: 122987 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3191. Min Act: -0.1700
Data Index: 1003144 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3191. Min Act: -0.1700
Data Index: 1057809 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3027. Min Act: -0.1700
Data Index: 880375 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.2862. Min Act: -0.1700
Data Index: 600338 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.2862. Min Act: -0.1700
Data Index: 844905 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.2862. Min Act: -0.1700
Data Index: 1341890 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.2862. Min Act: -0.1700
Data Index: 727027 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3027. Min Act: -0.1700
Data Index: 785724 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.3027. Min Act: -0.1700
Data Index: 827618 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.2862. Min Act: -0.1700
Data Index: 1504451 (Python Code)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.2862. Min Act: -0.1700
Data Index: 365494 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.2697. Min Act: -0.1700
Data Index: 1354527 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.2862. Min Act: -0.1700
Data Index: 912488 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4009. Min Range: -2.4009
Max Act: 2.2862. Min Act: -0.1700
Data Index: 272102 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19