Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 222 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.9669. Min Act: -0.1700
Data Index: 1350176 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.9352. Min Act: -0.1700
Data Index: 663036 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.9035. Min Act: -0.1700
Data Index: 538662 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.8718. Min Act: -0.1700
Data Index: 488555 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.8559. Min Act: -0.1700
Data Index: 943496 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.8400. Min Act: -0.1700
Data Index: 1216411 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.8241. Min Act: -0.1700
Data Index: 891152 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.8082. Min Act: -0.1700
Data Index: 310805 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.8082. Min Act: -0.1700
Data Index: 637857 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.8082. Min Act: -0.1700
Data Index: 1343432 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.8082. Min Act: -0.1700
Data Index: 755862 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.7763. Min Act: -0.1700
Data Index: 889132 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.7763. Min Act: -0.1700
Data Index: 13792 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.7922. Min Act: -0.1700
Data Index: 818388 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.7763. Min Act: -0.1700
Data Index: 74905 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.7922. Min Act: -0.1700
Data Index: 1327993 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.7444. Min Act: -0.1700
Data Index: 1216165 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.7604. Min Act: -0.1700
Data Index: 975423 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.7284. Min Act: -0.1700
Data Index: 383503 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9669. Min Range: -2.9669
Max Act: 2.7444. Min Act: -0.1700
Data Index: 1091762 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19