Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 501 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.8125. Min Act: -0.1700
Data Index: 1656222 (Python Code)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.7968. Min Act: -0.1700
Data Index: 1621051 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.6873. Min Act: -0.1700
Data Index: 1624809 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.6717. Min Act: -0.1700
Data Index: 1399087 (Python Code)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.6560. Min Act: -0.1700
Data Index: 1420778 (Python Code)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.6404. Min Act: -0.1700
Data Index: 1367217 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.6247. Min Act: -0.1700
Data Index: 1402410 (Python Code)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.6404. Min Act: -0.1700
Data Index: 1543536 (Python Code)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.6091. Min Act: -0.1700
Data Index: 1604467 (Python Code)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.6091. Min Act: -0.1700
Data Index: 1361044 (Python Code)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.6091. Min Act: -0.1700
Data Index: 1496085 (Python Code)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.5778. Min Act: -0.1700
Data Index: 1509773 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.5934. Min Act: -0.1700
Data Index: 1508748 (Python Code)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.5778. Min Act: -0.1700
Data Index: 1538630 (Python Code)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.5621. Min Act: -0.1700
Data Index: 1393114 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.5621. Min Act: -0.1700
Data Index: 1378305 (Python Code)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.5621. Min Act: -0.1700
Data Index: 1454166 (Python Code)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.5778. Min Act: -0.1700
Data Index: 1548798 (Python Code)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.5464. Min Act: -0.1700
Data Index: 1490386 (Python Code)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8125. Min Range: -3.8125
Max Act: 3.5621. Min Act: -0.1700
Data Index: 1570999 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19