Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1626 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.0330. Min Range: -6.0330
Max Act: 6.0330. Min Act: -0.1700
Data Index: 909479 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.9705. Min Act: -0.1700
Data Index: 933686 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0330. Min Range: -6.0330
Max Act: 6.0017. Min Act: -0.1700
Data Index: 1216938 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.9705. Min Act: -0.1700
Data Index: 912421 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0330. Min Range: -6.0330
Max Act: 6.0017. Min Act: -0.1700
Data Index: 304360 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.9392. Min Act: -0.1700
Data Index: 886051 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.9705. Min Act: -0.1700
Data Index: 214200 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.9392. Min Act: -0.1700
Data Index: 480997 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.9080. Min Act: -0.1700
Data Index: 114876 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.9080. Min Act: -0.1700
Data Index: 188535 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.8455. Min Act: -0.1700
Data Index: 1220980 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.8455. Min Act: -0.1700
Data Index: 972854 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.7830. Min Act: -0.1700
Data Index: 893928 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.7205. Min Act: -0.1700
Data Index: 1257613 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.7205. Min Act: -0.1700
Data Index: 1335597 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.7205. Min Act: -0.1700
Data Index: 1152164 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.7205. Min Act: -0.1700
Data Index: 833676 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.6580. Min Act: -0.1700
Data Index: 1133055 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.6892. Min Act: -0.1699
Data Index: 938459 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0330. Min Range: -6.0330
Max Act: 5.6892. Min Act: -0.1700
Data Index: 1015529 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19