Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.7097. Min Act: -0.1700
Data Index: 2472954 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.5847. Min Act: -0.1700
Data Index: 1853870 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.5222. Min Act: -0.1700
Data Index: 5420305 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.3347. Min Act: -0.1700
Data Index: 7572601 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.2097. Min Act: -0.1700
Data Index: 7501890 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.2722. Min Act: -0.1700
Data Index: 2319702 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.2097. Min Act: -0.1700
Data Index: 2002119 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.2097. Min Act: -0.1700
Data Index: 617816 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.1472. Min Act: -0.1700
Data Index: 1764752 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.1472. Min Act: -0.1700
Data Index: 2464868 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.1472. Min Act: -0.1700
Data Index: 6758287 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.0847. Min Act: -0.1700
Data Index: 4513211 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.0847. Min Act: -0.1700
Data Index: 2986118 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.0847. Min Act: -0.1700
Data Index: 707804 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.0847. Min Act: -0.1700
Data Index: 5825761 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.0847. Min Act: -0.1700
Data Index: 3681319 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.0847. Min Act: -0.1700
Data Index: 3745356 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.0222. Min Act: -0.1700
Data Index: 3107476 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.0222. Min Act: -0.1700
Data Index: 4291211 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7097. Min Range: -8.7097
Max Act: 8.0222. Min Act: -0.1700
Data Index: 4040383 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19