Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 97 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.7377. Min Act: -0.1700
Data Index: 1585265 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6897. Min Act: -0.1700
Data Index: 583969 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6577. Min Act: -0.1700
Data Index: 646565 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6577. Min Act: -0.1700
Data Index: 313577 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6577. Min Act: -0.1700
Data Index: 27917 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6577. Min Act: -0.1700
Data Index: 194669 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6416. Min Act: -0.1700
Data Index: 933924 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6577. Min Act: -0.1700
Data Index: 370422 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6416. Min Act: -0.1700
Data Index: 649467 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6256. Min Act: -0.1700
Data Index: 906573 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6416. Min Act: -0.1700
Data Index: 641277 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6256. Min Act: -0.1700
Data Index: 495890 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6416. Min Act: -0.1700
Data Index: 757199 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6256. Min Act: -0.1700
Data Index: 60980 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.5934. Min Act: -0.1700
Data Index: 220960 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.5934. Min Act: -0.1700
Data Index: 1079181 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6095. Min Act: -0.1700
Data Index: 361033 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6095. Min Act: -0.1700
Data Index: 236818 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.6095. Min Act: -0.1700
Data Index: 856827 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7377. Min Range: -2.7377
Max Act: 2.5934. Min Act: -0.1700
Data Index: 868934 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19