Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.8635. Min Act: -0.1700
Data Index: 8788804 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.5197. Min Act: -0.1700
Data Index: 162283 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.4260. Min Act: -0.1700
Data Index: 4690007 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.3947. Min Act: -0.1700
Data Index: 4824069 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.3947. Min Act: -0.1700
Data Index: 1648237 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.3635. Min Act: -0.1700
Data Index: 268103 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.3322. Min Act: -0.1700
Data Index: 5038053 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.3635. Min Act: -0.1700
Data Index: 6437421 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.3322. Min Act: -0.1700
Data Index: 4850679 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.3010. Min Act: -0.1700
Data Index: 755577 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.3322. Min Act: -0.1700
Data Index: 4004931 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.2697. Min Act: -0.1700
Data Index: 4763399 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.2385. Min Act: -0.1700
Data Index: 5896272 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.2385. Min Act: -0.1700
Data Index: 6570148 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.2385. Min Act: -0.1700
Data Index: 5262935 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.2385. Min Act: -0.1700
Data Index: 800547 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.2385. Min Act: -0.1700
Data Index: 7402542 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.1760. Min Act: -0.1700
Data Index: 833266 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.2072. Min Act: -0.1700
Data Index: 3616281 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8635. Min Range: -6.8635
Max Act: 6.2072. Min Act: -0.1700
Data Index: 2178116 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19