Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0881. Min Range: -6.0881
Max Act: 6.0881. Min Act: -0.1700
Data Index: 5132835 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0881. Min Range: -6.0881
Max Act: 6.0256. Min Act: -0.1700
Data Index: 1656643 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.8068. Min Act: -0.1700
Data Index: 3346097 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.7131. Min Act: -0.1700
Data Index: 2569462 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.7131. Min Act: -0.1700
Data Index: 1796002 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.7443. Min Act: -0.1700
Data Index: 7341904 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.6818. Min Act: -0.1700
Data Index: 5436653 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.6506. Min Act: -0.1700
Data Index: 3716903 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.6506. Min Act: -0.1700
Data Index: 318122 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.6818. Min Act: -0.1700
Data Index: 6307473 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.6193. Min Act: -0.1700
Data Index: 5253625 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.5568. Min Act: -0.1700
Data Index: 6281223 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.4943. Min Act: -0.1700
Data Index: 969378 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.4943. Min Act: -0.1700
Data Index: 7629070 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.4943. Min Act: -0.1700
Data Index: 8425619 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.4943. Min Act: -0.1700
Data Index: 3991317 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.4631. Min Act: -0.1700
Data Index: 1560733 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.4943. Min Act: -0.1700
Data Index: 6188465 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.4631. Min Act: -0.1700
Data Index: 4857083 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0881. Min Range: -6.0881
Max Act: 5.4631. Min Act: -0.1700
Data Index: 6754143 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19