Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1866 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6939. Min Act: -0.1700
Data Index: 746697 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6779. Min Act: -0.1700
Data Index: 332209 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6619. Min Act: -0.1700
Data Index: 57597 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6137. Min Act: -0.1700
Data Index: 1049278 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6298. Min Act: -0.1700
Data Index: 414850 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6298. Min Act: -0.1700
Data Index: 1208128 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6137. Min Act: -0.1700
Data Index: 702072 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6137. Min Act: -0.1700
Data Index: 113788 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6137. Min Act: -0.1700
Data Index: 1008074 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.6137. Min Act: -0.1700
Data Index: 540338 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5815. Min Act: -0.1700
Data Index: 439306 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5815. Min Act: -0.1700
Data Index: 1296675 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5976. Min Act: -0.1700
Data Index: 4965 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5976. Min Act: -0.1700
Data Index: 844602 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5976. Min Act: -0.1700
Data Index: 965516 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5815. Min Act: -0.1700
Data Index: 858153 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5654. Min Act: -0.1700
Data Index: 1180129 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5815. Min Act: -0.1700
Data Index: 215478 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5654. Min Act: -0.1700
Data Index: 212626 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6939. Min Range: -2.6939
Max Act: 2.5654. Min Act: -0.1700
Data Index: 887535 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19