Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 111 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.9632. Min Act: -0.1700
Data Index: 1205058 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.7445. Min Act: -0.1700
Data Index: 374031 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.7757. Min Act: -0.1700
Data Index: 633457 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.7445. Min Act: -0.1700
Data Index: 1220811 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.6820. Min Act: -0.1700
Data Index: 49487 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.6507. Min Act: -0.1700
Data Index: 750601 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.6195. Min Act: -0.1700
Data Index: 1352697 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.6195. Min Act: -0.1700
Data Index: 591317 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.6195. Min Act: -0.1700
Data Index: 183202 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.5569. Min Act: -0.1700
Data Index: 771483 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.5882. Min Act: -0.1700
Data Index: 174415 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.5882. Min Act: -0.1700
Data Index: 853381 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.5882. Min Act: -0.1700
Data Index: 811436 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.5569. Min Act: -0.1700
Data Index: 719002 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.5257. Min Act: -0.1700
Data Index: 150172 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.5569. Min Act: -0.1700
Data Index: 1249658 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.5569. Min Act: -0.1700
Data Index: 1157135 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.4944. Min Act: -0.1700
Data Index: 901029 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.5257. Min Act: -0.1700
Data Index: 160774 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9632. Min Range: -4.9632
Max Act: 4.4944. Min Act: -0.1700
Data Index: 1309674 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19