Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0512. Min Range: -8.0512
Max Act: 8.0512. Min Act: -0.1700
Data Index: 5634552 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.9887. Min Act: -0.1700
Data Index: 6793451 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.7387. Min Act: -0.1700
Data Index: 3708351 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.8012. Min Act: -0.1700
Data Index: 7864845 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.8637. Min Act: -0.1700
Data Index: 5464561 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.6137. Min Act: -0.1700
Data Index: 5682846 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.5512. Min Act: -0.1700
Data Index: 3406946 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.4887. Min Act: -0.1700
Data Index: 6475630 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.4887. Min Act: -0.1700
Data Index: 808068 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.5512. Min Act: -0.1700
Data Index: 713011 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.4262. Min Act: -0.1700
Data Index: 2779311 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.4262. Min Act: -0.1700
Data Index: 2476954 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.4262. Min Act: -0.1700
Data Index: 5774758 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.3637. Min Act: -0.1700
Data Index: 1370769 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.3637. Min Act: -0.1700
Data Index: 4803728 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.3324. Min Act: -0.1700
Data Index: 8721159 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.3324. Min Act: -0.1700
Data Index: 844091 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.3637. Min Act: -0.1700
Data Index: 3117416 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.3012. Min Act: -0.1700
Data Index: 6280890 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0512. Min Range: -8.0512
Max Act: 7.3324. Min Act: -0.1700
Data Index: 8042233 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19