Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4706 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0717. Min Range: -8.0717
Max Act: 8.0717. Min Act: -0.1700
Data Index: 8689923 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0717. Min Range: -8.0717
Max Act: 8.0717. Min Act: -0.1700
Data Index: 4383845 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.8842. Min Act: -0.1700
Data Index: 3634941 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.8842. Min Act: -0.1700
Data Index: 6393965 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.6654. Min Act: -0.1700
Data Index: 2011430 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.5092. Min Act: -0.1700
Data Index: 4380246 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.4154. Min Act: -0.1700
Data Index: 375331 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.4154. Min Act: -0.1700
Data Index: 8644601 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.4154. Min Act: -0.1700
Data Index: 7344378 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.3529. Min Act: -0.1700
Data Index: 1917418 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.3217. Min Act: -0.1700
Data Index: 2049765 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.2904. Min Act: -0.1700
Data Index: 6852533 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.2904. Min Act: -0.1700
Data Index: 1829190 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.2592. Min Act: -0.1700
Data Index: 114796 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.2904. Min Act: -0.1700
Data Index: 5981458 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.2592. Min Act: -0.1700
Data Index: 6861305 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.2592. Min Act: -0.1700
Data Index: 462386 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.2279. Min Act: -0.1700
Data Index: 6156883 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.2279. Min Act: -0.1700
Data Index: 4791072 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0717. Min Range: -8.0717
Max Act: 7.2279. Min Act: -0.1700
Data Index: 6873795 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19