Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1026. Min Range: -6.1026
Max Act: 6.1026. Min Act: -0.1700
Data Index: 67890 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.8526. Min Act: -0.1700
Data Index: 3222824 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.7901. Min Act: -0.1700
Data Index: 67888 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.7589. Min Act: -0.1700
Data Index: 6745098 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.7589. Min Act: -0.1700
Data Index: 3419998 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.7589. Min Act: -0.1700
Data Index: 6350470 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.7276. Min Act: -0.1700
Data Index: 2071490 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.6964. Min Act: -0.1700
Data Index: 4027002 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.7276. Min Act: -0.1700
Data Index: 8717353 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.6964. Min Act: -0.1700
Data Index: 67889 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.6651. Min Act: -0.1700
Data Index: 5852637 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.6651. Min Act: -0.1700
Data Index: 3222825 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.6651. Min Act: -0.1700
Data Index: 1012336 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.6339. Min Act: -0.1700
Data Index: 5579407 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.5714. Min Act: -0.1700
Data Index: 7908070 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.5401. Min Act: -0.1700
Data Index: 7979216 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.5401. Min Act: -0.1700
Data Index: 4393439 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.5401. Min Act: -0.1700
Data Index: 4674555 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.5401. Min Act: -0.1700
Data Index: 1637890 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1026. Min Range: -6.1026
Max Act: 5.5401. Min Act: -0.1700
Data Index: 5515297 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19