Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1919 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.8626. Min Act: -0.1700
Data Index: 63177 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.8626. Min Act: -0.1700
Data Index: 757441 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7990. Min Act: -0.1700
Data Index: 1046920 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.8149. Min Act: -0.1700
Data Index: 1248435 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7831. Min Act: -0.1700
Data Index: 684204 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7831. Min Act: -0.1700
Data Index: 1410691 (Python Code)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7831. Min Act: -0.1700
Data Index: 1005030 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7831. Min Act: -0.1700
Data Index: 147770 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7671. Min Act: -0.1700
Data Index: 1192240 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7671. Min Act: -0.1700
Data Index: 1398043 (Python Code)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7352. Min Act: -0.1700
Data Index: 484102 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7352. Min Act: -0.1700
Data Index: 1267103 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7512. Min Act: -0.1700
Data Index: 246333 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7512. Min Act: -0.1700
Data Index: 1095171 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7671. Min Act: -0.1700
Data Index: 333312 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7512. Min Act: -0.1700
Data Index: 1466644 (Python Code)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7192. Min Act: -0.1700
Data Index: 1601178 (Python Code)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7352. Min Act: -0.1700
Data Index: 1397652 (Python Code)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7512. Min Act: -0.1700
Data Index: 1429744 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8626. Min Range: -2.8626
Max Act: 2.7192. Min Act: -0.1700
Data Index: 1360096 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19