Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1998 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.6140. Min Act: -0.1700
Data Index: 1269389 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.5515. Min Act: -0.1700
Data Index: 314491 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.5515. Min Act: -0.1700
Data Index: 1044865 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.5515. Min Act: -0.1700
Data Index: 1301012 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.5202. Min Act: -0.1700
Data Index: 1328436 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.5202. Min Act: -0.1700
Data Index: 449214 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.4265. Min Act: -0.1700
Data Index: 518304 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.4265. Min Act: -0.1700
Data Index: 1042411 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.4265. Min Act: -0.1700
Data Index: 620830 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.4577. Min Act: -0.1700
Data Index: 1086487 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.4265. Min Act: -0.1700
Data Index: 397687 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.3640. Min Act: -0.1700
Data Index: 81150 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.3952. Min Act: -0.1700
Data Index: 808554 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.3327. Min Act: -0.1700
Data Index: 642055 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.3952. Min Act: -0.1700
Data Index: 167417 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.3640. Min Act: -0.1700
Data Index: 670333 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.3327. Min Act: -0.1700
Data Index: 263566 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.3327. Min Act: -0.1700
Data Index: 441689 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.3327. Min Act: -0.1700
Data Index: 105699 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6140. Min Range: -4.6140
Max Act: 4.2702. Min Act: -0.1700
Data Index: 869600 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19