Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 367 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.4291. Min Act: -0.1700
Data Index: 784659 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.4128. Min Act: -0.1700
Data Index: 297213 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.3965. Min Act: -0.1700
Data Index: 1000670 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.3802. Min Act: -0.1700
Data Index: 1484657 (Python Code)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.2818. Min Act: -0.1700
Data Index: 926431 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.2818. Min Act: -0.1700
Data Index: 997421 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.2488. Min Act: -0.1700
Data Index: 956364 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.2488. Min Act: -0.1700
Data Index: 566091 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.2653. Min Act: -0.1700
Data Index: 994948 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.2323. Min Act: -0.1700
Data Index: 999781 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.2488. Min Act: -0.1700
Data Index: 1145707 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.2157. Min Act: -0.1700
Data Index: 461884 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.2157. Min Act: -0.1700
Data Index: 1324284 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.1992. Min Act: -0.1700
Data Index: 1187775 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.1992. Min Act: -0.1700
Data Index: 641399 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.1826. Min Act: -0.1700
Data Index: 929850 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.1992. Min Act: -0.1700
Data Index: 538151 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.1826. Min Act: -0.1700
Data Index: 541875 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.1826. Min Act: -0.1700
Data Index: 570693 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4291. Min Range: -2.4291
Max Act: 2.1826. Min Act: -0.1700
Data Index: 1189105 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19