Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 151 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.6987. Min Act: -0.1700
Data Index: 888748 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.6830. Min Act: -0.1700
Data Index: 630033 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.6361. Min Act: -0.1700
Data Index: 420061 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.5891. Min Act: -0.1700
Data Index: 640840 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.5108. Min Act: -0.1700
Data Index: 471205 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4951. Min Act: -0.1700
Data Index: 195508 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4795. Min Act: -0.1700
Data Index: 1053501 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4951. Min Act: -0.1700
Data Index: 1141082 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4795. Min Act: -0.1700
Data Index: 680471 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4951. Min Act: -0.1700
Data Index: 1212074 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4638. Min Act: -0.1700
Data Index: 851650 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4638. Min Act: -0.1700
Data Index: 547028 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4481. Min Act: -0.1700
Data Index: 543162 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4481. Min Act: -0.1700
Data Index: 917162 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4481. Min Act: -0.1700
Data Index: 1050900 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4168. Min Act: -0.1700
Data Index: 955559 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4324. Min Act: -0.1700
Data Index: 426746 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4168. Min Act: -0.1700
Data Index: 880951 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4481. Min Act: -0.1700
Data Index: 942659 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6987. Min Range: -3.6987
Max Act: 3.4324. Min Act: -0.1700
Data Index: 579161 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19