Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1701. Min Range: -6.1701
Max Act: 6.1701. Min Act: -0.1700
Data Index: 2739416 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1701. Min Range: -6.1701
Max Act: 6.1389. Min Act: -0.1700
Data Index: 692826 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4177757 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.8576. Min Act: -0.1700
Data Index: 1828738 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.8264. Min Act: -0.1700
Data Index: 6403591 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.7639. Min Act: -0.1700
Data Index: 3189303 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.7639. Min Act: -0.1700
Data Index: 7805417 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.7326. Min Act: -0.1700
Data Index: 6963953 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.7014. Min Act: -0.1700
Data Index: 3849548 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.7014. Min Act: -0.1700
Data Index: 464764 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.7014. Min Act: -0.1700
Data Index: 4703687 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.7014. Min Act: -0.1700
Data Index: 604317 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.6701. Min Act: -0.1700
Data Index: 5088289 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.6389. Min Act: -0.1700
Data Index: 8316195 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.6701. Min Act: -0.1700
Data Index: 3948012 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.6389. Min Act: -0.1700
Data Index: 7207009 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.6389. Min Act: -0.1700
Data Index: 8272756 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.6076. Min Act: -0.1700
Data Index: 3578509 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.6076. Min Act: -0.1700
Data Index: 6640379 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1701. Min Range: -6.1701
Max Act: 5.5764. Min Act: -0.1700
Data Index: 3528237 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19