Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2042 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4943. Min Act: -0.1700
Data Index: 1527486 (Python Code)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.4318. Min Act: -0.1700
Data Index: 1376023 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.2443. Min Act: -0.1700
Data Index: 1514353 (Python Code)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.2130. Min Act: -0.1700
Data Index: 1244008 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.1505. Min Act: -0.1700
Data Index: 1390491 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.1817. Min Act: -0.1700
Data Index: 1631300 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.2130. Min Act: -0.1700
Data Index: 1495671 (Python Code)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.1505. Min Act: -0.1700
Data Index: 687490 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.1505. Min Act: -0.1700
Data Index: 1621980 (Python Code)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.1817. Min Act: -0.1700
Data Index: 1630628 (Python Code)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.1192. Min Act: -0.1700
Data Index: 1548367 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.0567. Min Act: -0.1700
Data Index: 1612513 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.1505. Min Act: -0.1700
Data Index: 1599353 (Python Code)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.1192. Min Act: -0.1700
Data Index: 1427315 (Python Code)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.0880. Min Act: -0.1700
Data Index: 1596165 (Python Code)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.0567. Min Act: -0.1700
Data Index: 58940 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.0567. Min Act: -0.1700
Data Index: 1374700 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.0567. Min Act: -0.1700
Data Index: 1372722 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.0880. Min Act: -0.1700
Data Index: 1480039 (Python Code)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4943. Min Range: -4.4943
Max Act: 4.0567. Min Act: -0.1700
Data Index: 1550650 (Python Code)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19