Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1746 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1700. Min Range: -3.1700
Max Act: 3.1700. Min Act: -0.1700
Data Index: 246787 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1700. Min Range: -3.1700
Max Act: 3.1543. Min Act: -0.1700
Data Index: 257399 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1700. Min Range: -3.1700
Max Act: 3.0755. Min Act: -0.1700
Data Index: 1548465 (Python Code)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1700. Min Range: -3.1700
Max Act: 3.0439. Min Act: -0.1700
Data Index: 554545 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1700. Min Range: -3.1700
Max Act: 3.0439. Min Act: -0.1700
Data Index: 850626 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1700. Min Range: -3.1700
Max Act: 3.0597. Min Act: -0.1700
Data Index: 1161067 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9807. Min Act: -0.1700
Data Index: 800305 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9965. Min Act: -0.1700
Data Index: 183577 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9807. Min Act: -0.1700
Data Index: 1154528 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9649. Min Act: -0.1700
Data Index: 1253363 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9807. Min Act: -0.1700
Data Index: 1488295 (Python Code)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9491. Min Act: -0.1700
Data Index: 1526727 (Python Code)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9332. Min Act: -0.1700
Data Index: 1340027 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9649. Min Act: -0.1700
Data Index: 800030 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9332. Min Act: -0.1700
Data Index: 1479160 (Python Code)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9174. Min Act: -0.1700
Data Index: 233007 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9174. Min Act: -0.1700
Data Index: 574396 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9174. Min Act: -0.1700
Data Index: 692736 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9015. Min Act: -0.1700
Data Index: 1629204 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1700. Min Range: -3.1700
Max Act: 2.9015. Min Act: -0.1700
Data Index: 889146 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19