Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 584 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1218. Min Range: -2.1218
Max Act: 2.1218. Min Act: -0.1700
Data Index: 1138266 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1218. Min Range: -2.1218
Max Act: 2.0716. Min Act: -0.1700
Data Index: 403520 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1218. Min Range: -2.1218
Max Act: 2.0380. Min Act: -0.1700
Data Index: 1593964 (Python Code)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1218. Min Range: -2.1218
Max Act: 2.0212. Min Act: -0.1700
Data Index: 1610836 (Python Code)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1218. Min Range: -2.1218
Max Act: 2.0212. Min Act: -0.1699
Data Index: 1510575 (Python Code)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1218. Min Range: -2.1218
Max Act: 2.0212. Min Act: -0.1700
Data Index: 1402385 (Python Code)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1218. Min Range: -2.1218
Max Act: 2.0212. Min Act: -0.1700
Data Index: 1556107 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9959. Min Act: -0.1700
Data Index: 1529997 (Python Code)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9959. Min Act: -0.1700
Data Index: 1399667 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9874. Min Act: -0.1700
Data Index: 1026604 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9959. Min Act: -0.1700
Data Index: 1609154 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9874. Min Act: -0.1700
Data Index: 1332388 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9790. Min Act: -0.1700
Data Index: 1381652 (Python Code)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9705. Min Act: -0.1700
Data Index: 629481 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9620. Min Act: -0.1700
Data Index: 1549641 (Python Code)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9705. Min Act: -0.1700
Data Index: 1401849 (Python Code)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9451. Min Act: -0.1700
Data Index: 378371 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9620. Min Act: -0.1700
Data Index: 384329 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9451. Min Act: -0.1700
Data Index: 1438259 (Python Code)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1218. Min Range: -2.1218
Max Act: 1.9536. Min Act: -0.1700
Data Index: 1567617 (Python Code)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19