Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1942 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.4223. Min Act: -0.1700
Data Index: 338446 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.3285. Min Act: -0.1700
Data Index: 853919 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2973. Min Act: -0.1700
Data Index: 147767 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.3285. Min Act: -0.1700
Data Index: 779211 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2660. Min Act: -0.1700
Data Index: 840458 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2660. Min Act: -0.1700
Data Index: 870655 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2660. Min Act: -0.1700
Data Index: 222094 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2973. Min Act: -0.1700
Data Index: 471183 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2973. Min Act: -0.1700
Data Index: 986849 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2660. Min Act: -0.1700
Data Index: 353966 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2035. Min Act: -0.1700
Data Index: 819328 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.3285. Min Act: -0.1700
Data Index: 526462 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.1410. Min Act: -0.1700
Data Index: 122383 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2348. Min Act: -0.1700
Data Index: 286073 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2660. Min Act: -0.1700
Data Index: 337828 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2348. Min Act: -0.1700
Data Index: 1085091 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2348. Min Act: -0.1700
Data Index: 1148869 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2348. Min Act: -0.1700
Data Index: 186789 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2348. Min Act: -0.1700
Data Index: 1077145 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4223. Min Range: -4.4223
Max Act: 4.2035. Min Act: -0.1700
Data Index: 1341038 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19