Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1321 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.9437. Min Act: -0.1700
Data Index: 876255 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.8500. Min Act: -0.1700
Data Index: 798971 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.8187. Min Act: -0.1700
Data Index: 26971 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.8187. Min Act: -0.1700
Data Index: 97419 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.7875. Min Act: -0.1700
Data Index: 186132 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.7562. Min Act: -0.1700
Data Index: 1282169 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.7875. Min Act: -0.1700
Data Index: 304193 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.7562. Min Act: -0.1700
Data Index: 38275 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.7250. Min Act: -0.1700
Data Index: 483940 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6625. Min Act: -0.1700
Data Index: 140998 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 769719 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 124935 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6312. Min Act: -0.1700
Data Index: 73261 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6625. Min Act: -0.1700
Data Index: 607289 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6937. Min Act: -0.1700
Data Index: 849625 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6312. Min Act: -0.1700
Data Index: 315433 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6625. Min Act: -0.1700
Data Index: 376878 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6312. Min Act: -0.1700
Data Index: 394060 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6312. Min Act: -0.1700
Data Index: 1226970 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9437. Min Range: -4.9437
Max Act: 4.6312. Min Act: -0.1700
Data Index: 510828 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19