Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 525 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.3160. Min Act: -0.1700
Data Index: 1541778 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.2847. Min Act: -0.1700
Data Index: 649116 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.3160. Min Act: -0.1700
Data Index: 1383270 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.2847. Min Act: -0.1700
Data Index: 1479358 (Python Code)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.2222. Min Act: -0.1700
Data Index: 1421412 (Python Code)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.1910. Min Act: -0.1700
Data Index: 1376420 (Python Code)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.1597. Min Act: -0.1700
Data Index: 1510703 (Python Code)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.1597. Min Act: -0.1700
Data Index: 1579838 (Python Code)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.1285. Min Act: -0.1700
Data Index: 1459704 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.1285. Min Act: -0.1700
Data Index: 1610997 (Python Code)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0972. Min Act: -0.1699
Data Index: 388448 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0972. Min Act: -0.1700
Data Index: 1637803 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0659. Min Act: -0.1700
Data Index: 1442343 (Python Code)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0659. Min Act: -0.1700
Data Index: 1411531 (Python Code)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0659. Min Act: -0.1700
Data Index: 1539578 (Python Code)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0659. Min Act: -0.1700
Data Index: 1444106 (Python Code)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0659. Min Act: -0.1700
Data Index: 926784 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0034. Min Act: -0.1700
Data Index: 1522545 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0034. Min Act: -0.1700
Data Index: 1509517 (Python Code)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3160. Min Range: -4.3160
Max Act: 4.0347. Min Act: -0.1700
Data Index: 1631268 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19