Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4021 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.9246. Min Act: -0.1700
Data Index: 1474461 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.9246. Min Act: -0.1700
Data Index: 265606 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.8933. Min Act: -0.1700
Data Index: 3485596 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.8621. Min Act: -0.1700
Data Index: 5938225 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.8621. Min Act: -0.1700
Data Index: 7490886 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7996. Min Act: -0.1700
Data Index: 119267 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.8308. Min Act: -0.1700
Data Index: 5594551 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.8621. Min Act: -0.1700
Data Index: 7626089 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.8308. Min Act: -0.1700
Data Index: 4906371 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7996. Min Act: -0.1700
Data Index: 1907772 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7683. Min Act: -0.1700
Data Index: 1527014 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7996. Min Act: -0.1700
Data Index: 2567447 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.8621. Min Act: -0.1700
Data Index: 4899549 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7996. Min Act: -0.1700
Data Index: 3692380 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7683. Min Act: -0.1700
Data Index: 2497939 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7058. Min Act: -0.1700
Data Index: 5521151 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7058. Min Act: -0.1700
Data Index: 6897295 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7683. Min Act: -0.1700
Data Index: 8352390 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.6746. Min Act: -0.1700
Data Index: 6621626 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.6746. Min Act: -0.1700
Data Index: 6813447 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19