Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.4629. Min Act: -0.1700
Data Index: 6243901 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.4004. Min Act: -0.1700
Data Index: 8713625 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.4004. Min Act: -0.1700
Data Index: 3224180 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.2754. Min Act: -0.1700
Data Index: 7059758 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.2754. Min Act: -0.1700
Data Index: 5085070 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.2754. Min Act: -0.1700
Data Index: 8279100 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.2754. Min Act: -0.1700
Data Index: 663256 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.1504. Min Act: -0.1700
Data Index: 973905 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.1504. Min Act: -0.1700
Data Index: 4179423 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.1504. Min Act: -0.1700
Data Index: 4652896 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.0254. Min Act: -0.1700
Data Index: 6746060 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.0254. Min Act: -0.1700
Data Index: 4576525 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4629. Min Range: -8.4629
Max Act: 7.9629. Min Act: -0.1700
Data Index: 2725323 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.0254. Min Act: -0.1700
Data Index: 7059767 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4629. Min Range: -8.4629
Max Act: 8.0254. Min Act: -0.1700
Data Index: 2725328 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4629. Min Range: -8.4629
Max Act: 7.9629. Min Act: -0.1700
Data Index: 2725325 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4629. Min Range: -8.4629
Max Act: 7.9629. Min Act: -0.1700
Data Index: 1013886 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4629. Min Range: -8.4629
Max Act: 7.9629. Min Act: -0.1700
Data Index: 7059753 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4629. Min Range: -8.4629
Max Act: 7.9629. Min Act: -0.1700
Data Index: 973906 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4629. Min Range: -8.4629
Max Act: 7.9629. Min Act: -0.1700
Data Index: 2725327 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19