Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2042 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0425. Min Range: -3.0425
Max Act: 3.0425. Min Act: -0.1700
Data Index: 2714 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9951. Min Act: -0.1700
Data Index: 947304 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0425. Min Range: -3.0425
Max Act: 3.0109. Min Act: -0.1700
Data Index: 554796 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9635. Min Act: -0.1700
Data Index: 794968 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9635. Min Act: -0.1700
Data Index: 92036 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9318. Min Act: -0.1700
Data Index: 628217 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9476. Min Act: -0.1700
Data Index: 855311 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9793. Min Act: -0.1700
Data Index: 1038211 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9318. Min Act: -0.1700
Data Index: 297183 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9476. Min Act: -0.1700
Data Index: 331032 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9476. Min Act: -0.1700
Data Index: 1327034 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9159. Min Act: -0.1700
Data Index: 1241427 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9318. Min Act: -0.1700
Data Index: 1311416 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9318. Min Act: -0.1700
Data Index: 1284137 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9159. Min Act: -0.1700
Data Index: 854392 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9318. Min Act: -0.1700
Data Index: 344873 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9159. Min Act: -0.1700
Data Index: 9830 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9159. Min Act: -0.1700
Data Index: 732836 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.9001. Min Act: -0.1700
Data Index: 833701 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0425. Min Range: -3.0425
Max Act: 2.8842. Min Act: -0.1700
Data Index: 127587 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19