Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2312 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.5499. Min Act: -0.1700
Data Index: 8467901 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.4874. Min Act: -0.1700
Data Index: 515552 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.2999. Min Act: -0.1700
Data Index: 7314102 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.2999. Min Act: -0.1700
Data Index: 3747645 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.2686. Min Act: -0.1700
Data Index: 4424528 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.2686. Min Act: -0.1700
Data Index: 4572621 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.2374. Min Act: -0.1700
Data Index: 2945696 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.2374. Min Act: -0.1700
Data Index: 599490 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.2061. Min Act: -0.1700
Data Index: 3492789 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1749. Min Act: -0.1700
Data Index: 6847550 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1749. Min Act: -0.1700
Data Index: 6408702 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1749. Min Act: -0.1700
Data Index: 3648031 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1749. Min Act: -0.1700
Data Index: 7576 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1749. Min Act: -0.1700
Data Index: 2019153 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1749. Min Act: -0.1700
Data Index: 8602897 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1749. Min Act: -0.1700
Data Index: 5250080 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1749. Min Act: -0.1700
Data Index: 1701615 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1749. Min Act: -0.1700
Data Index: 8026529 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1436. Min Act: -0.1700
Data Index: 1210014 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5499. Min Range: -5.5499
Max Act: 5.1436. Min Act: -0.1700
Data Index: 6389348 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19