Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3277 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.5253. Min Act: -0.1700
Data Index: 8654002 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.4628. Min Act: -0.1700
Data Index: 5680354 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.4315. Min Act: -0.1700
Data Index: 8184043 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.4315. Min Act: -0.1700
Data Index: 5680353 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.3065. Min Act: -0.1700
Data Index: 901315 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2753. Min Act: -0.1700
Data Index: 5062763 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2753. Min Act: -0.1700
Data Index: 8609979 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2753. Min Act: -0.1700
Data Index: 2642377 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2440. Min Act: -0.1700
Data Index: 4753985 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2753. Min Act: -0.1700
Data Index: 5680349 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2128. Min Act: -0.1700
Data Index: 6085715 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2128. Min Act: -0.1700
Data Index: 4208898 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2128. Min Act: -0.1700
Data Index: 4517295 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1815. Min Act: -0.1700
Data Index: 2048572 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1815. Min Act: -0.1700
Data Index: 418397 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1815. Min Act: -0.1700
Data Index: 4108382 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1190. Min Act: -0.1700
Data Index: 8184040 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1503. Min Act: -0.1700
Data Index: 3212065 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1815. Min Act: -0.1700
Data Index: 5680340 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1503. Min Act: -0.1700
Data Index: 4361469 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19