Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2487 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.6721. Min Act: -0.1700
Data Index: 3455013 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.6096. Min Act: -0.1700
Data Index: 6108064 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.4221. Min Act: -0.1700
Data Index: 5496693 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.4221. Min Act: -0.1700
Data Index: 2395425 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.3909. Min Act: -0.1700
Data Index: 2737297 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.3909. Min Act: -0.1700
Data Index: 6046594 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.3596. Min Act: -0.1700
Data Index: 247311 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2971. Min Act: -0.1700
Data Index: 3585413 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2971. Min Act: -0.1700
Data Index: 4509485 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2659. Min Act: -0.1700
Data Index: 7491981 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2659. Min Act: -0.1700
Data Index: 7519117 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2659. Min Act: -0.1700
Data Index: 8372267 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2659. Min Act: -0.1700
Data Index: 2341342 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2659. Min Act: -0.1700
Data Index: 2621778 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2346. Min Act: -0.1700
Data Index: 2748271 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2346. Min Act: -0.1700
Data Index: 6996605 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2346. Min Act: -0.1700
Data Index: 805310 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2346. Min Act: -0.1700
Data Index: 5252385 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2034. Min Act: -0.1700
Data Index: 5908382 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6721. Min Range: -5.6721
Max Act: 5.2034. Min Act: -0.1700
Data Index: 5629280 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19