Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2033 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0545. Min Range: -4.0545
Max Act: 4.0545. Min Act: -0.1700
Data Index: 105802 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0545. Min Range: -4.0545
Max Act: 4.0545. Min Act: -0.1700
Data Index: 1181303 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.9607. Min Act: -0.1700
Data Index: 892256 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.9607. Min Act: -0.1700
Data Index: 317771 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.9607. Min Act: -0.1700
Data Index: 1146774 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.9607. Min Act: -0.1700
Data Index: 836232 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.9920. Min Act: -0.1700
Data Index: 911717 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8982. Min Act: -0.1700
Data Index: 911126 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8669. Min Act: -0.1700
Data Index: 801285 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8669. Min Act: -0.1700
Data Index: 336571 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8669. Min Act: -0.1700
Data Index: 191360 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8669. Min Act: -0.1700
Data Index: 559430 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8669. Min Act: -0.1700
Data Index: 1102076 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8357. Min Act: -0.1700
Data Index: 220868 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.7887. Min Act: -0.1700
Data Index: 229986 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8200. Min Act: -0.1700
Data Index: 1289759 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.7887. Min Act: -0.1700
Data Index: 162408 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8044. Min Act: -0.1700
Data Index: 1285822 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.7887. Min Act: -0.1700
Data Index: 360478 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0545. Min Range: -4.0545
Max Act: 3.8044. Min Act: -0.1700
Data Index: 59544 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19