Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 435 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1565. Min Range: -3.1565
Max Act: 3.1565. Min Act: -0.1700
Data Index: 498288 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1565. Min Range: -3.1565
Max Act: 3.1565. Min Act: -0.1700
Data Index: 1304958 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.9829. Min Act: -0.1700
Data Index: 746197 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.9829. Min Act: -0.1700
Data Index: 816080 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.9513. Min Act: -0.1700
Data Index: 1153865 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.9196. Min Act: -0.1700
Data Index: 388064 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.9354. Min Act: -0.1700
Data Index: 147559 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.9354. Min Act: -0.1700
Data Index: 193680 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.9354. Min Act: -0.1700
Data Index: 1289656 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8879. Min Act: -0.1700
Data Index: 873227 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.9037. Min Act: -0.1700
Data Index: 363540 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8402. Min Act: -0.1700
Data Index: 575339 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8879. Min Act: -0.1700
Data Index: 1132212 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8561. Min Act: -0.1700
Data Index: 1342062 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8402. Min Act: -0.1700
Data Index: 964428 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8243. Min Act: -0.1700
Data Index: 587866 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8402. Min Act: -0.1700
Data Index: 742156 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8402. Min Act: -0.1700
Data Index: 925867 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8243. Min Act: -0.1700
Data Index: 1115180 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1565. Min Range: -3.1565
Max Act: 2.8402. Min Act: -0.1700
Data Index: 1065014 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19