Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.2808. Min Act: -0.1700
Data Index: 1522126 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.2183. Min Act: -0.1700
Data Index: 2125492 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.2495. Min Act: -0.1700
Data Index: 7562696 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.2183. Min Act: -0.1700
Data Index: 8183821 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.1558. Min Act: -0.1700
Data Index: 3511423 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.1870. Min Act: -0.1700
Data Index: 5054869 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.1870. Min Act: -0.1700
Data Index: 4408928 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.1558. Min Act: -0.1700
Data Index: 4519006 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.1558. Min Act: -0.1700
Data Index: 6437776 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0620. Min Act: -0.1700
Data Index: 4164630 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.1245. Min Act: -0.1700
Data Index: 136867 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0308. Min Act: -0.1700
Data Index: 3376656 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0620. Min Act: -0.1700
Data Index: 1127607 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0620. Min Act: -0.1700
Data Index: 8243780 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0620. Min Act: -0.1700
Data Index: 6881385 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0620. Min Act: -0.1700
Data Index: 4348658 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0620. Min Act: -0.1700
Data Index: 5994025 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0933. Min Act: -0.1700
Data Index: 956784 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0308. Min Act: -0.1700
Data Index: 3236587 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2808. Min Range: -5.2808
Max Act: 5.0308. Min Act: -0.1700
Data Index: 258574 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19