Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1692 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.4697. Min Act: -0.1700
Data Index: 487239 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.4072. Min Act: -0.1700
Data Index: 745514 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.3135. Min Act: -0.1700
Data Index: 872729 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.3447. Min Act: -0.1700
Data Index: 350597 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.2822. Min Act: -0.1700
Data Index: 413856 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.1885. Min Act: -0.1700
Data Index: 772352 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.1885. Min Act: -0.1700
Data Index: 1142053 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.1260. Min Act: -0.1700
Data Index: 1256665 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.1260. Min Act: -0.1700
Data Index: 1183382 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.0947. Min Act: -0.1700
Data Index: 596873 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.0322. Min Act: -0.1700
Data Index: 566446 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.0322. Min Act: -0.1700
Data Index: 1176742 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4697. Min Range: -6.4697
Max Act: 5.9385. Min Act: -0.1700
Data Index: 894425 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4697. Min Range: -6.4697
Max Act: 6.0010. Min Act: -0.1700
Data Index: 87616 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4697. Min Range: -6.4697
Max Act: 5.9697. Min Act: -0.1700
Data Index: 767888 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4697. Min Range: -6.4697
Max Act: 5.9697. Min Act: -0.1700
Data Index: 742365 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4697. Min Range: -6.4697
Max Act: 5.9072. Min Act: -0.1700
Data Index: 801361 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4697. Min Range: -6.4697
Max Act: 5.9385. Min Act: -0.1700
Data Index: 1214417 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4697. Min Range: -6.4697
Max Act: 5.9385. Min Act: -0.1700
Data Index: 387957 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4697. Min Range: -6.4697
Max Act: 5.8760. Min Act: -0.1700
Data Index: 573884 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19