Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1964 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.6605. Min Act: -0.1700
Data Index: 20218 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.6123. Min Act: -0.1700
Data Index: 1246140 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5962. Min Act: -0.1700
Data Index: 1258185 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5801. Min Act: -0.1700
Data Index: 1117739 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5317. Min Act: -0.1700
Data Index: 212839 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5479. Min Act: -0.1700
Data Index: 1318519 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5640. Min Act: -0.1700
Data Index: 623900 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5317. Min Act: -0.1700
Data Index: 189103 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5156. Min Act: -0.1700
Data Index: 1301582 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5156. Min Act: -0.1700
Data Index: 124270 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.4994. Min Act: -0.1700
Data Index: 1009791 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.4994. Min Act: -0.1700
Data Index: 619167 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5156. Min Act: -0.1700
Data Index: 858821 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.5156. Min Act: -0.1700
Data Index: 849572 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.4832. Min Act: -0.1700
Data Index: 708567 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.4832. Min Act: -0.1700
Data Index: 711252 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.4994. Min Act: -0.1700
Data Index: 1264478 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.4669. Min Act: -0.1700
Data Index: 525694 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.4832. Min Act: -0.1700
Data Index: 262625 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6605. Min Range: -2.6605
Max Act: 2.4832. Min Act: -0.1700
Data Index: 553246 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19