Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0387. Min Range: -7.0387
Max Act: 7.0387. Min Act: -0.1700
Data Index: 287302 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0387. Min Range: -7.0387
Max Act: 7.0387. Min Act: -0.1700
Data Index: 4480933 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.9449. Min Act: -0.1700
Data Index: 81444 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.9137. Min Act: -0.1700
Data Index: 872845 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.8824. Min Act: -0.1700
Data Index: 6333883 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.8512. Min Act: -0.1700
Data Index: 1880675 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.7887. Min Act: -0.1700
Data Index: 4212475 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.7887. Min Act: -0.1700
Data Index: 3242630 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.7887. Min Act: -0.1700
Data Index: 7250471 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.7574. Min Act: -0.1700
Data Index: 6068367 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.7574. Min Act: -0.1700
Data Index: 5165213 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.7574. Min Act: -0.1700
Data Index: 8574249 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.7262. Min Act: -0.1700
Data Index: 826867 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.7574. Min Act: -0.1700
Data Index: 84245 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.6949. Min Act: -0.1700
Data Index: 3406809 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.6637. Min Act: -0.1700
Data Index: 4727280 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.6637. Min Act: -0.1700
Data Index: 8221378 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.6324. Min Act: -0.1700
Data Index: 7363887 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.6012. Min Act: -0.1700
Data Index: 7027094 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0387. Min Range: -7.0387
Max Act: 6.5699. Min Act: -0.1700
Data Index: 2764658 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19