Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 902 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.2100. Min Range: -5.2100
Max Act: 5.2100. Min Act: -0.1700
Data Index: 1154305 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2100. Min Range: -5.2100
Max Act: 5.0225. Min Act: -0.1700
Data Index: 1275933 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.8350. Min Act: -0.1700
Data Index: 917046 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.8350. Min Act: -0.1700
Data Index: 1117431 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.7725. Min Act: -0.1700
Data Index: 260281 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.8037. Min Act: -0.1700
Data Index: 523394 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.7725. Min Act: -0.1700
Data Index: 928917 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.7725. Min Act: -0.1700
Data Index: 827006 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.7412. Min Act: -0.1700
Data Index: 239370 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.8037. Min Act: -0.1700
Data Index: 450358 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.7100. Min Act: -0.1700
Data Index: 645341 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.7412. Min Act: -0.1700
Data Index: 439968 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.6787. Min Act: -0.1700
Data Index: 352168 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.7412. Min Act: -0.1700
Data Index: 1342100 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.7100. Min Act: -0.1700
Data Index: 1078293 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.6475. Min Act: -0.1700
Data Index: 483959 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.6787. Min Act: -0.1700
Data Index: 82813 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.6475. Min Act: -0.1700
Data Index: 744833 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.6787. Min Act: -0.1700
Data Index: 4699 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2100. Min Range: -5.2100
Max Act: 4.7100. Min Act: -0.1700
Data Index: 1052923 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19