Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2902 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3950. Min Range: -6.3950
Max Act: 6.3950. Min Act: -0.1700
Data Index: 1019139 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3950. Min Range: -6.3950
Max Act: 6.3638. Min Act: -0.1700
Data Index: 4149507 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3950. Min Range: -6.3950
Max Act: 6.2075. Min Act: -0.1700
Data Index: 7085619 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3950. Min Range: -6.3950
Max Act: 6.2388. Min Act: -0.1700
Data Index: 6171214 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3950. Min Range: -6.3950
Max Act: 6.1138. Min Act: -0.1700
Data Index: 623520 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3950. Min Range: -6.3950
Max Act: 6.0825. Min Act: -0.1700
Data Index: 4548667 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3950. Min Range: -6.3950
Max Act: 6.0825. Min Act: -0.1700
Data Index: 6577698 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3950. Min Range: -6.3950
Max Act: 6.0513. Min Act: -0.1700
Data Index: 6815995 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3950. Min Range: -6.3950
Max Act: 6.0200. Min Act: -0.1700
Data Index: 2179189 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.9888. Min Act: -0.1700
Data Index: 7154500 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.9888. Min Act: -0.1700
Data Index: 918501 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.9888. Min Act: -0.1700
Data Index: 7563404 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.9888. Min Act: -0.1700
Data Index: 4483391 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.9888. Min Act: -0.1700
Data Index: 8554853 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.9575. Min Act: -0.1700
Data Index: 1067951 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.8950. Min Act: -0.1700
Data Index: 7668146 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.8638. Min Act: -0.1700
Data Index: 4861075 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.8950. Min Act: -0.1700
Data Index: 420389 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.8638. Min Act: -0.1700
Data Index: 654713 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3950. Min Range: -6.3950
Max Act: 5.8325. Min Act: -0.1700
Data Index: 7771517 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19