Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1013 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1956. Min Act: -0.1699
Data Index: 356415 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1790. Min Act: -0.1700
Data Index: 1261010 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1457. Min Act: -0.1700
Data Index: 1245927 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1457. Min Act: -0.1700
Data Index: 130950 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1290. Min Act: -0.1700
Data Index: 967018 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1290. Min Act: -0.1700
Data Index: 489948 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1123. Min Act: -0.1699
Data Index: 1375229 (Python Code)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1123. Min Act: -0.1699
Data Index: 1603341 (Python Code)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1123. Min Act: -0.1700
Data Index: 529177 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1290. Min Act: -0.1700
Data Index: 253682 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.1123. Min Act: -0.1700
Data Index: 1274878 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.0956. Min Act: -0.1700
Data Index: 1252794 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.0956. Min Act: -0.1700
Data Index: 1005363 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.0956. Min Act: -0.1699
Data Index: 1417772 (Python Code)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.0956. Min Act: -0.1699
Data Index: 1397918 (Python Code)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.0956. Min Act: -0.1700
Data Index: 164704 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.0789. Min Act: -0.1700
Data Index: 221521 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.0789. Min Act: -0.1700
Data Index: 861598 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.0789. Min Act: -0.1700
Data Index: 324689 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1956. Min Range: -2.1956
Max Act: 2.0453. Min Act: -0.1696
Data Index: 1392576 (Python Code)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19