Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 315 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0726. Min Range: -6.0726
Max Act: 6.0726. Min Act: -0.1700
Data Index: 2625067 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.8851. Min Act: -0.1700
Data Index: 5441719 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.8851. Min Act: -0.1700
Data Index: 122167 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7914. Min Act: -0.1700
Data Index: 5845805 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7914. Min Act: -0.1700
Data Index: 2178910 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.6976. Min Act: -0.1700
Data Index: 5145193 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7289. Min Act: -0.1700
Data Index: 6651527 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.6976. Min Act: -0.1700
Data Index: 122168 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7289. Min Act: -0.1700
Data Index: 6264382 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.6976. Min Act: -0.1700
Data Index: 7048425 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.6664. Min Act: -0.1700
Data Index: 2261113 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.6351. Min Act: -0.1700
Data Index: 5551000 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.6664. Min Act: -0.1700
Data Index: 4345952 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.6039. Min Act: -0.1700
Data Index: 6866680 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.5414. Min Act: -0.1700
Data Index: 1954902 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.6039. Min Act: -0.1700
Data Index: 7865533 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.5101. Min Act: -0.1700
Data Index: 43268 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.5414. Min Act: -0.1700
Data Index: 6123513 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.5414. Min Act: -0.1700
Data Index: 5329799 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.5101. Min Act: -0.1700
Data Index: 253725 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19