Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1465 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2729. Min Range: -3.2729
Max Act: 3.2729. Min Act: -0.1700
Data Index: 136590 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2729. Min Range: -3.2729
Max Act: 3.0524. Min Act: -0.1700
Data Index: 815320 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.9892. Min Act: -0.1700
Data Index: 840103 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.9576. Min Act: -0.1700
Data Index: 720770 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.9576. Min Act: -0.1700
Data Index: 1349979 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.9892. Min Act: -0.1700
Data Index: 96036 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.9417. Min Act: -0.1700
Data Index: 545474 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8942. Min Act: -0.1700
Data Index: 735903 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8942. Min Act: -0.1700
Data Index: 808417 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8783. Min Act: -0.1700
Data Index: 132139 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.9259. Min Act: -0.1700
Data Index: 891728 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.9100. Min Act: -0.1700
Data Index: 201851 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8783. Min Act: -0.1700
Data Index: 255706 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8942. Min Act: -0.1700
Data Index: 1171593 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.9100. Min Act: -0.1700
Data Index: 1164945 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8942. Min Act: -0.1700
Data Index: 1160639 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8942. Min Act: -0.1700
Data Index: 433929 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8624. Min Act: -0.1700
Data Index: 931596 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8942. Min Act: -0.1700
Data Index: 955602 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2729. Min Range: -3.2729
Max Act: 2.8942. Min Act: -0.1700
Data Index: 356735 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19