Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1953 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.1110. Min Act: -0.1700
Data Index: 882611 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0479. Min Act: -0.1700
Data Index: 97588 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0321. Min Act: -0.1700
Data Index: 261763 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0163. Min Act: -0.1700
Data Index: 296102 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0321. Min Act: -0.1700
Data Index: 964896 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0163. Min Act: -0.1700
Data Index: 836072 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0005. Min Act: -0.1700
Data Index: 1101913 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0005. Min Act: -0.1700
Data Index: 327830 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0321. Min Act: -0.1700
Data Index: 262244 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0005. Min Act: -0.1700
Data Index: 863409 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1110. Min Range: -3.1110
Max Act: 2.9847. Min Act: -0.1700
Data Index: 1131118 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0005. Min Act: -0.1700
Data Index: 424046 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0005. Min Act: -0.1700
Data Index: 698156 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1110. Min Range: -3.1110
Max Act: 3.0163. Min Act: -0.1700
Data Index: 966919 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1110. Min Range: -3.1110
Max Act: 2.9847. Min Act: -0.1700
Data Index: 914090 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1110. Min Range: -3.1110
Max Act: 2.9689. Min Act: -0.1700
Data Index: 392054 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1110. Min Range: -3.1110
Max Act: 2.9689. Min Act: -0.1700
Data Index: 37367 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1110. Min Range: -3.1110
Max Act: 2.9531. Min Act: -0.1700
Data Index: 482705 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1110. Min Range: -3.1110
Max Act: 2.9689. Min Act: -0.1700
Data Index: 741948 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1110. Min Range: -3.1110
Max Act: 2.9531. Min Act: -0.1700
Data Index: 262679 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19