Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1889 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.8954. Min Act: -0.1700
Data Index: 1485591 (Python Code)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.8954. Min Act: -0.1700
Data Index: 1466676 (Python Code)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.8796. Min Act: -0.1700
Data Index: 103172 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.8160. Min Act: -0.1700
Data Index: 270018 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.8160. Min Act: -0.1700
Data Index: 1023799 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.8001. Min Act: -0.1700
Data Index: 1215045 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7841. Min Act: -0.1700
Data Index: 1065574 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7841. Min Act: -0.1700
Data Index: 1021587 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7522. Min Act: -0.1700
Data Index: 581762 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7522. Min Act: -0.1700
Data Index: 1215486 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7522. Min Act: -0.1700
Data Index: 680806 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7203. Min Act: -0.1700
Data Index: 292267 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7203. Min Act: -0.1700
Data Index: 1350257 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7203. Min Act: -0.1700
Data Index: 128079 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7203. Min Act: -0.1700
Data Index: 737171 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7203. Min Act: -0.1700
Data Index: 142771 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7043. Min Act: -0.1700
Data Index: 616954 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7203. Min Act: -0.1700
Data Index: 382415 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.6883. Min Act: -0.1700
Data Index: 280670 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8954. Min Range: -2.8954
Max Act: 2.7203. Min Act: -0.1700
Data Index: 867312 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19