Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1971 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.3889. Min Act: -0.1700
Data Index: 815739 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.1389. Min Act: -0.1700
Data Index: 1216886 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.1389. Min Act: -0.1700
Data Index: 378086 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.1389. Min Act: -0.1700
Data Index: 3326 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0764. Min Act: -0.1700
Data Index: 222489 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0764. Min Act: -0.1700
Data Index: 845441 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0764. Min Act: -0.1700
Data Index: 783221 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0451. Min Act: -0.1700
Data Index: 1184492 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0451. Min Act: -0.1700
Data Index: 395071 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0451. Min Act: -0.1700
Data Index: 544980 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0138. Min Act: -0.1700
Data Index: 1010238 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0138. Min Act: -0.1700
Data Index: 579429 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0138. Min Act: -0.1700
Data Index: 881886 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3889. Min Range: -4.3889
Max Act: 3.9826. Min Act: -0.1700
Data Index: 924421 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3889. Min Range: -4.3889
Max Act: 3.9826. Min Act: -0.1700
Data Index: 916598 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3889. Min Range: -4.3889
Max Act: 3.9826. Min Act: -0.1700
Data Index: 1138642 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3889. Min Range: -4.3889
Max Act: 4.0138. Min Act: -0.1700
Data Index: 448983 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3889. Min Range: -4.3889
Max Act: 3.9826. Min Act: -0.1700
Data Index: 627857 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3889. Min Range: -4.3889
Max Act: 3.9513. Min Act: -0.1700
Data Index: 133306 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3889. Min Range: -4.3889
Max Act: 3.9513. Min Act: -0.1700
Data Index: 326101 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19