Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.4223. Min Act: -0.1700
Data Index: 8282270 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.3285. Min Act: -0.1700
Data Index: 6723540 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.2973. Min Act: -0.1700
Data Index: 772516 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.2973. Min Act: -0.1700
Data Index: 6740008 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.2660. Min Act: -0.1700
Data Index: 6890448 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.2035. Min Act: -0.1700
Data Index: 7161630 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.2035. Min Act: -0.1700
Data Index: 6627854 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.1723. Min Act: -0.1700
Data Index: 5582103 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.1723. Min Act: -0.1700
Data Index: 2562407 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.1410. Min Act: -0.1700
Data Index: 7072402 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.1410. Min Act: -0.1700
Data Index: 8524198 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.1098. Min Act: -0.1700
Data Index: 5902716 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.1098. Min Act: -0.1700
Data Index: 3458234 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.0785. Min Act: -0.1700
Data Index: 5305420 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.1098. Min Act: -0.1700
Data Index: 7282345 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.0785. Min Act: -0.1700
Data Index: 3098401 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.0473. Min Act: -0.1700
Data Index: 7146164 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.0473. Min Act: -0.1700
Data Index: 6549204 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.0785. Min Act: -0.1700
Data Index: 3544904 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4223. Min Range: -6.4223
Max Act: 6.0473. Min Act: -0.1700
Data Index: 8150227 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19