Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1551 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.5524. Min Act: -0.1700
Data Index: 428219 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.3901. Min Act: -0.1700
Data Index: 1653317 (Python Code)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.3737. Min Act: -0.1700
Data Index: 1369663 (Python Code)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.3901. Min Act: -0.1700
Data Index: 1369822 (Python Code)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.3574. Min Act: -0.1700
Data Index: 794345 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.3246. Min Act: -0.1700
Data Index: 1425622 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.3246. Min Act: -0.1700
Data Index: 564933 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.3082. Min Act: -0.1700
Data Index: 1414675 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.2918. Min Act: -0.1700
Data Index: 1591752 (Python Code)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.2588. Min Act: -0.1700
Data Index: 157994 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.2423. Min Act: -0.1700
Data Index: 1414318 (Python Code)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.2092. Min Act: -0.1700
Data Index: 1057689 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.2092. Min Act: -0.1700
Data Index: 1638962 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.2258. Min Act: -0.1700
Data Index: 507071 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.1926. Min Act: -0.1700
Data Index: 811778 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.2092. Min Act: -0.1700
Data Index: 897788 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.1926. Min Act: -0.1700
Data Index: 1367344 (Python Code)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.1926. Min Act: -0.1700
Data Index: 509696 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.1926. Min Act: -0.1700
Data Index: 1177285 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5524. Min Range: -2.5524
Max Act: 2.1926. Min Act: -0.1700
Data Index: 377907 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19