Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1924 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.3289. Min Act: -0.1700
Data Index: 889387 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.1727. Min Act: -0.1700
Data Index: 479311 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.1414. Min Act: -0.1700
Data Index: 228072 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.1414. Min Act: -0.1700
Data Index: 112444 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.1414. Min Act: -0.1700
Data Index: 751122 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.1101. Min Act: -0.1700
Data Index: 143660 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.1101. Min Act: -0.1700
Data Index: 461166 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0789. Min Act: -0.1700
Data Index: 1097467 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.1101. Min Act: -0.1700
Data Index: 1236328 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.1101. Min Act: -0.1700
Data Index: 243627 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0476. Min Act: -0.1700
Data Index: 440067 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0476. Min Act: -0.1700
Data Index: 585130 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0476. Min Act: -0.1700
Data Index: 1139644 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0163. Min Act: -0.1700
Data Index: 606318 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0163. Min Act: -0.1700
Data Index: 871352 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0163. Min Act: -0.1700
Data Index: 442029 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3289. Min Range: -4.3289
Max Act: 3.9851. Min Act: -0.1700
Data Index: 422308 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0163. Min Act: -0.1700
Data Index: 793210 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0163. Min Act: -0.1700
Data Index: 366412 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3289. Min Range: -4.3289
Max Act: 4.0163. Min Act: -0.1700
Data Index: 904881 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19