Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.2672. Min Act: -0.1700
Data Index: 4675279 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.2047. Min Act: -0.1700
Data Index: 2209627 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.1422. Min Act: -0.1700
Data Index: 4582761 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.1109. Min Act: -0.1700
Data Index: 3110155 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.1109. Min Act: -0.1700
Data Index: 2435694 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.0797. Min Act: -0.1700
Data Index: 6236344 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.0484. Min Act: -0.1700
Data Index: 583814 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.0484. Min Act: -0.1700
Data Index: 6381205 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.0171. Min Act: -0.1700
Data Index: 4863600 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.0171. Min Act: -0.1700
Data Index: 7582070 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.0171. Min Act: -0.1700
Data Index: 3721135 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.0171. Min Act: -0.1700
Data Index: 850310 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2672. Min Range: -4.2672
Max Act: 4.0171. Min Act: -0.1700
Data Index: 5738371 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2672. Min Range: -4.2672
Max Act: 3.9859. Min Act: -0.1700
Data Index: 8807420 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2672. Min Range: -4.2672
Max Act: 3.9859. Min Act: -0.1700
Data Index: 3625133 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2672. Min Range: -4.2672
Max Act: 3.9859. Min Act: -0.1700
Data Index: 360172 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2672. Min Range: -4.2672
Max Act: 3.9859. Min Act: -0.1700
Data Index: 5938710 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2672. Min Range: -4.2672
Max Act: 3.9859. Min Act: -0.1700
Data Index: 5640850 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2672. Min Range: -4.2672
Max Act: 3.9859. Min Act: -0.1700
Data Index: 1364839 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2672. Min Range: -4.2672
Max Act: 3.9546. Min Act: -0.1700
Data Index: 5589995 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19