Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 157 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.3310. Min Act: -0.1700
Data Index: 694661 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.3146. Min Act: -0.1700
Data Index: 936656 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2982. Min Act: -0.1700
Data Index: 652748 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2982. Min Act: -0.1700
Data Index: 1305678 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2487. Min Act: -0.1700
Data Index: 1407151 (Python Code)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2322. Min Act: -0.1700
Data Index: 493401 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2322. Min Act: -0.1700
Data Index: 410827 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2487. Min Act: -0.1700
Data Index: 1095072 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2322. Min Act: -0.1700
Data Index: 170967 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2487. Min Act: -0.1700
Data Index: 1031150 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2322. Min Act: -0.1700
Data Index: 380762 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2157. Min Act: -0.1700
Data Index: 1497824 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.1991. Min Act: -0.1700
Data Index: 1609942 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2322. Min Act: -0.1700
Data Index: 1330749 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2157. Min Act: -0.1700
Data Index: 254333 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2157. Min Act: -0.1700
Data Index: 204106 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2157. Min Act: -0.1700
Data Index: 824491 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.1991. Min Act: -0.1700
Data Index: 1212634 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.2157. Min Act: -0.1700
Data Index: 1145729 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3310. Min Range: -2.3310
Max Act: 2.1991. Min Act: -0.1700
Data Index: 63848 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19