Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3307 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1461. Min Range: -5.1461
Max Act: 5.1461. Min Act: -0.1700
Data Index: 6230069 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1461. Min Range: -5.1461
Max Act: 5.1149. Min Act: -0.1700
Data Index: 7337071 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1461. Min Range: -5.1461
Max Act: 5.0524. Min Act: -0.1700
Data Index: 2632620 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1461. Min Range: -5.1461
Max Act: 5.0524. Min Act: -0.1700
Data Index: 2151628 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1461. Min Range: -5.1461
Max Act: 5.0836. Min Act: -0.1700
Data Index: 4308359 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1461. Min Range: -5.1461
Max Act: 5.0211. Min Act: -0.1700
Data Index: 4716849 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1461. Min Range: -5.1461
Max Act: 5.0524. Min Act: -0.1700
Data Index: 1379253 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1461. Min Range: -5.1461
Max Act: 5.0211. Min Act: -0.1700
Data Index: 8165657 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9899. Min Act: -0.1700
Data Index: 6867021 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9899. Min Act: -0.1700
Data Index: 5724633 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9899. Min Act: -0.1700
Data Index: 5467909 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9586. Min Act: -0.1700
Data Index: 753050 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9899. Min Act: -0.1700
Data Index: 3609626 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9899. Min Act: -0.1700
Data Index: 5541198 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1461. Min Range: -5.1461
Max Act: 5.0211. Min Act: -0.1700
Data Index: 730571 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9899. Min Act: -0.1700
Data Index: 3079764 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9586. Min Act: -0.1700
Data Index: 189053 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9274. Min Act: -0.1700
Data Index: 818239 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9274. Min Act: -0.1700
Data Index: 936240 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1461. Min Range: -5.1461
Max Act: 4.9586. Min Act: -0.1700
Data Index: 4720642 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19