Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1753 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.8469. Min Act: -0.1700
Data Index: 778912 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.8156. Min Act: -0.1700
Data Index: 833260 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.6906. Min Act: -0.1700
Data Index: 1004972 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.5656. Min Act: -0.1700
Data Index: 331719 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.6281. Min Act: -0.1700
Data Index: 689718 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.5968. Min Act: -0.1700
Data Index: 352104 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.5968. Min Act: -0.1700
Data Index: 1235938 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.5968. Min Act: -0.1700
Data Index: 1509048 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.5656. Min Act: -0.1700
Data Index: 407760 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.5968. Min Act: -0.1700
Data Index: 663324 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.4406. Min Act: -0.1700
Data Index: 467578 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.5031. Min Act: -0.1700
Data Index: 1420694 (Python Code)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.4718. Min Act: -0.1700
Data Index: 777399 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.5343. Min Act: -0.1700
Data Index: 1071326 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.4718. Min Act: -0.1700
Data Index: 43920 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.4718. Min Act: -0.1700
Data Index: 151461 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.5031. Min Act: -0.1700
Data Index: 575625 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.4718. Min Act: -0.1700
Data Index: 1134071 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.4718. Min Act: -0.1700
Data Index: 1092485 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8469. Min Range: -4.8469
Max Act: 4.4718. Min Act: -0.1700
Data Index: 481490 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19