Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 902 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.9350. Min Act: -0.1700
Data Index: 595287 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.9038. Min Act: -0.1700
Data Index: 122577 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.8725. Min Act: -0.1700
Data Index: 1010468 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.8100. Min Act: -0.1700
Data Index: 405177 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.8413. Min Act: -0.1700
Data Index: 1344611 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.7788. Min Act: -0.1700
Data Index: 815089 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.8100. Min Act: -0.1700
Data Index: 914580 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.8100. Min Act: -0.1700
Data Index: 775982 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.7475. Min Act: -0.1700
Data Index: 1078313 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.8100. Min Act: -0.1700
Data Index: 63854 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.7163. Min Act: -0.1699
Data Index: 688217 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.7163. Min Act: -0.1700
Data Index: 1016412 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.7475. Min Act: -0.1700
Data Index: 229251 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.7475. Min Act: -0.1700
Data Index: 994674 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.7163. Min Act: -0.1699
Data Index: 1210394 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.6850. Min Act: -0.1700
Data Index: 878280 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.6850. Min Act: -0.1700
Data Index: 1176355 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.6850. Min Act: -0.1700
Data Index: 862451 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.6850. Min Act: -0.1700
Data Index: 428075 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9350. Min Range: -4.9350
Max Act: 4.6225. Min Act: -0.1700
Data Index: 1230848 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19