Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5837 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.2477. Min Act: -0.1700
Data Index: 3667251 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.1227. Min Act: -0.1700
Data Index: 4312914 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.1227. Min Act: -0.1700
Data Index: 5490019 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0915. Min Act: -0.1700
Data Index: 2113122 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0915. Min Act: -0.1700
Data Index: 3580064 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0915. Min Act: -0.1700
Data Index: 2587620 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0915. Min Act: -0.1700
Data Index: 7161137 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0602. Min Act: -0.1700
Data Index: 8073735 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0602. Min Act: -0.1700
Data Index: 1604438 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0602. Min Act: -0.1700
Data Index: 69363 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0915. Min Act: -0.1700
Data Index: 3038451 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2477. Min Range: -4.2477
Max Act: 3.9977. Min Act: -0.1700
Data Index: 280475 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0289. Min Act: -0.1700
Data Index: 710495 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0289. Min Act: -0.1700
Data Index: 6142458 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2477. Min Range: -4.2477
Max Act: 4.0602. Min Act: -0.1700
Data Index: 2906761 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2477. Min Range: -4.2477
Max Act: 3.9664. Min Act: -0.1700
Data Index: 5815630 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2477. Min Range: -4.2477
Max Act: 3.9664. Min Act: -0.1700
Data Index: 7480650 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2477. Min Range: -4.2477
Max Act: 3.9977. Min Act: -0.1700
Data Index: 4074096 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2477. Min Range: -4.2477
Max Act: 3.9352. Min Act: -0.1700
Data Index: 4297331 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2477. Min Range: -4.2477
Max Act: 3.9664. Min Act: -0.1700
Data Index: 205979 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19