Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 58 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0108. Min Range: -5.0108
Max Act: 5.0108. Min Act: -0.1700
Data Index: 913205 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.9171. Min Act: -0.1700
Data Index: 1137756 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.8546. Min Act: -0.1700
Data Index: 468032 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.8546. Min Act: -0.1700
Data Index: 1179409 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.8233. Min Act: -0.1700
Data Index: 1317118 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.7921. Min Act: -0.1700
Data Index: 1011759 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.7296. Min Act: -0.1700
Data Index: 902224 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.7296. Min Act: -0.1700
Data Index: 542091 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.7608. Min Act: -0.1700
Data Index: 88911 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.6983. Min Act: -0.1700
Data Index: 193553 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.7296. Min Act: -0.1700
Data Index: 980124 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.7608. Min Act: -0.1700
Data Index: 1207380 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.6983. Min Act: -0.1700
Data Index: 376138 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.6671. Min Act: -0.1700
Data Index: 331120 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.7296. Min Act: -0.1700
Data Index: 641255 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.6983. Min Act: -0.1700
Data Index: 186972 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.6671. Min Act: -0.1700
Data Index: 895072 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.6983. Min Act: -0.1700
Data Index: 1168467 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.6358. Min Act: -0.1700
Data Index: 875346 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0108. Min Range: -5.0108
Max Act: 4.6983. Min Act: -0.1700
Data Index: 370469 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19