Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1235 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.4881. Min Act: -0.1700
Data Index: 1524642 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.4557. Min Act: -0.1700
Data Index: 1392367 (Python Code)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.4719. Min Act: -0.1700
Data Index: 1508497 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.4557. Min Act: -0.1700
Data Index: 1447278 (Python Code)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.4557. Min Act: -0.1700
Data Index: 1596585 (Python Code)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.4231. Min Act: -0.1700
Data Index: 1413063 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.4231. Min Act: -0.1700
Data Index: 1618543 (Python Code)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.4231. Min Act: -0.1700
Data Index: 1536856 (Python Code)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.3742. Min Act: -0.1700
Data Index: 1398815 (Python Code)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.3742. Min Act: -0.1700
Data Index: 1390319 (Python Code)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.3578. Min Act: -0.1700
Data Index: 1501544 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.3415. Min Act: -0.1700
Data Index: 1556228 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.2922. Min Act: -0.1700
Data Index: 1591204 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.3086. Min Act: -0.1700
Data Index: 1611543 (Python Code)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.2922. Min Act: -0.1700
Data Index: 1443799 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.2757. Min Act: -0.1700
Data Index: 1215655 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.2592. Min Act: -0.1700
Data Index: 449528 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.2922. Min Act: -0.1700
Data Index: 1599402 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.2757. Min Act: -0.1700
Data Index: 1322536 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4881. Min Range: -2.4881
Max Act: 2.2592. Min Act: -0.1700
Data Index: 1518387 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19