Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1435 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.2884. Min Act: -0.1700
Data Index: 144926 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.2098. Min Act: -0.1700
Data Index: 147853 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.1941. Min Act: -0.1700
Data Index: 284343 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.1311. Min Act: -0.1700
Data Index: 1280565 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.1154. Min Act: -0.1700
Data Index: 894906 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.0365. Min Act: -0.1700
Data Index: 26215 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.0365. Min Act: -0.1700
Data Index: 409958 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.0365. Min Act: -0.1700
Data Index: 55710 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.0049. Min Act: -0.1700
Data Index: 31276 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.0207. Min Act: -0.1700
Data Index: 202297 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.0207. Min Act: -0.1700
Data Index: 986536 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2884. Min Range: -3.2884
Max Act: 3.0207. Min Act: -0.1700
Data Index: 1023431 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2884. Min Range: -3.2884
Max Act: 2.9891. Min Act: -0.1700
Data Index: 44376 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2884. Min Range: -3.2884
Max Act: 2.9733. Min Act: -0.1700
Data Index: 1344103 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2884. Min Range: -3.2884
Max Act: 2.9574. Min Act: -0.1700
Data Index: 333680 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2884. Min Range: -3.2884
Max Act: 2.9574. Min Act: -0.1700
Data Index: 768047 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2884. Min Range: -3.2884
Max Act: 2.9258. Min Act: -0.1700
Data Index: 200129 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2884. Min Range: -3.2884
Max Act: 2.9574. Min Act: -0.1700
Data Index: 63443 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2884. Min Range: -3.2884
Max Act: 2.9574. Min Act: -0.1700
Data Index: 1139520 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2884. Min Range: -3.2884
Max Act: 2.9099. Min Act: -0.1700
Data Index: 1132666 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19