Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1206 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.5162. Min Act: -0.1700
Data Index: 7408617 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.4849. Min Act: -0.1700
Data Index: 6590837 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.3287. Min Act: -0.1700
Data Index: 7298148 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2662. Min Act: -0.1700
Data Index: 2139136 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2662. Min Act: -0.1700
Data Index: 6358419 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2037. Min Act: -0.1700
Data Index: 8770245 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2037. Min Act: -0.1700
Data Index: 7188402 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2662. Min Act: -0.1700
Data Index: 3303586 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2349. Min Act: -0.1700
Data Index: 5949972 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2037. Min Act: -0.1700
Data Index: 4708139 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2037. Min Act: -0.1700
Data Index: 6368348 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2349. Min Act: -0.1700
Data Index: 7489712 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.1724. Min Act: -0.1700
Data Index: 6696282 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.1724. Min Act: -0.1700
Data Index: 8127333 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.1412. Min Act: -0.1700
Data Index: 3397027 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.1412. Min Act: -0.1700
Data Index: 2476418 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.1412. Min Act: -0.1700
Data Index: 1128230 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.1412. Min Act: -0.1700
Data Index: 6912205 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.1412. Min Act: -0.1700
Data Index: 3597164 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.1099. Min Act: -0.1700
Data Index: 715142 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19