Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5149 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.3036. Min Act: -0.1700
Data Index: 491561 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.3036. Min Act: -0.1700
Data Index: 6864531 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.2723. Min Act: -0.1700
Data Index: 493893 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.2098. Min Act: -0.1700
Data Index: 526404 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1786. Min Act: -0.1700
Data Index: 8400573 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1786. Min Act: -0.1700
Data Index: 5995280 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1786. Min Act: -0.1700
Data Index: 5007881 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1786. Min Act: -0.1699
Data Index: 766519 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1473. Min Act: -0.1700
Data Index: 5708351 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1473. Min Act: -0.1699
Data Index: 6536322 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1161. Min Act: -0.1699
Data Index: 6250274 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1473. Min Act: -0.1697
Data Index: 1069663 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1473. Min Act: -0.1700
Data Index: 644714 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1473. Min Act: -0.1700
Data Index: 1293625 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1473. Min Act: -0.1700
Data Index: 7662228 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1161. Min Act: -0.1700
Data Index: 2762522 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1161. Min Act: -0.1700
Data Index: 3886386 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1161. Min Act: -0.1700
Data Index: 6472531 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1161. Min Act: -0.1700
Data Index: 240738 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3036. Min Range: -6.3036
Max Act: 6.1161. Min Act: -0.1700
Data Index: 3201403 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19