Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2027 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.7722. Min Act: -0.1700
Data Index: 144295 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.4910. Min Act: -0.1700
Data Index: 1121854 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.3660. Min Act: -0.1700
Data Index: 256607 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.3972. Min Act: -0.1700
Data Index: 201041 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.3347. Min Act: -0.1700
Data Index: 819405 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.3660. Min Act: -0.1700
Data Index: 566229 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.3035. Min Act: -0.1700
Data Index: 713596 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.2410. Min Act: -0.1700
Data Index: 1006531 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.3035. Min Act: -0.1700
Data Index: 731177 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.2722. Min Act: -0.1700
Data Index: 699901 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.2410. Min Act: -0.1700
Data Index: 307724 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.2722. Min Act: -0.1700
Data Index: 520069 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.1784. Min Act: -0.1700
Data Index: 838890 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.2097. Min Act: -0.1700
Data Index: 734210 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.2410. Min Act: -0.1700
Data Index: 988151 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.2097. Min Act: -0.1700
Data Index: 335543 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.2097. Min Act: -0.1700
Data Index: 910125 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.1784. Min Act: -0.1700
Data Index: 906105 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.1472. Min Act: -0.1700
Data Index: 756605 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7722. Min Range: -4.7722
Max Act: 4.1784. Min Act: -0.1700
Data Index: 969041 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19