Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 301 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.8276. Min Act: -0.1700
Data Index: 977601 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7958. Min Act: -0.1700
Data Index: 623131 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7958. Min Act: -0.1700
Data Index: 1210667 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7479. Min Act: -0.1700
Data Index: 593046 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7479. Min Act: -0.1700
Data Index: 640831 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7320. Min Act: -0.1700
Data Index: 155997 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 222742 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7320. Min Act: -0.1700
Data Index: 329745 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 311266 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 216311 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 941805 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 53369 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 964919 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 472492 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7320. Min Act: -0.1700
Data Index: 505127 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 984685 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 1027891 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 1029168 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 1189249 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8276. Min Range: -2.8276
Max Act: 2.7160. Min Act: -0.1700
Data Index: 296978 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19