Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.7408. Min Act: -0.1700
Data Index: 5288365 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.5845. Min Act: -0.1700
Data Index: 7391901 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.5533. Min Act: -0.1700
Data Index: 4961048 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.5845. Min Act: -0.1700
Data Index: 3813828 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.5220. Min Act: -0.1700
Data Index: 948063 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.4908. Min Act: -0.1700
Data Index: 5010336 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.4595. Min Act: -0.1700
Data Index: 3597815 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.4595. Min Act: -0.1700
Data Index: 4961046 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.4595. Min Act: -0.1700
Data Index: 7682113 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.4595. Min Act: -0.1700
Data Index: 495206 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.4283. Min Act: -0.1700
Data Index: 5969978 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.4283. Min Act: -0.1700
Data Index: 422910 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.3970. Min Act: -0.1700
Data Index: 4362568 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.3033. Min Act: -0.1700
Data Index: 7026660 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.3345. Min Act: -0.1700
Data Index: 2795615 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.2720. Min Act: -0.1700
Data Index: 833353 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.3033. Min Act: -0.1699
Data Index: 2936893 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.3033. Min Act: -0.1700
Data Index: 2637296 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.3033. Min Act: -0.1700
Data Index: 5033956 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7408. Min Range: -5.7408
Max Act: 5.2720. Min Act: -0.1700
Data Index: 482631 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19