Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2000 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.3062. Min Act: -0.1700
Data Index: 95939 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.1812. Min Act: -0.1700
Data Index: 497232 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.1186. Min Act: -0.1700
Data Index: 1250967 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.1186. Min Act: -0.1700
Data Index: 738472 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.1186. Min Act: -0.1700
Data Index: 1054087 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.0561. Min Act: -0.1700
Data Index: 633833 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.0874. Min Act: -0.1700
Data Index: 744637 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.0874. Min Act: -0.1700
Data Index: 121028 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.0248. Min Act: -0.1700
Data Index: 178945 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.0248. Min Act: -0.1700
Data Index: 374866 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.0561. Min Act: -0.1700
Data Index: 467999 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3062. Min Range: -4.3062
Max Act: 4.0248. Min Act: -0.1700
Data Index: 449755 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3062. Min Range: -4.3062
Max Act: 3.9936. Min Act: -0.1700
Data Index: 718220 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3062. Min Range: -4.3062
Max Act: 3.9623. Min Act: -0.1700
Data Index: 862263 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3062. Min Range: -4.3062
Max Act: 3.9936. Min Act: -0.1700
Data Index: 201318 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3062. Min Range: -4.3062
Max Act: 3.9623. Min Act: -0.1700
Data Index: 1045115 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3062. Min Range: -4.3062
Max Act: 3.9310. Min Act: -0.1700
Data Index: 1230504 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3062. Min Range: -4.3062
Max Act: 3.8998. Min Act: -0.1700
Data Index: 1289270 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3062. Min Range: -4.3062
Max Act: 3.9310. Min Act: -0.1700
Data Index: 918250 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3062. Min Range: -4.3062
Max Act: 3.8998. Min Act: -0.1700
Data Index: 752940 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19