Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.3115. Min Act: -0.1700
Data Index: 3983955 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.3427. Min Act: -0.1700
Data Index: 2293222 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.3115. Min Act: -0.1700
Data Index: 1686463 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.2177. Min Act: -0.1700
Data Index: 3414187 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.2177. Min Act: -0.1700
Data Index: 1380581 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.1552. Min Act: -0.1700
Data Index: 4710827 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.1240. Min Act: -0.1700
Data Index: 418464 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.1240. Min Act: -0.1700
Data Index: 7480750 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.0927. Min Act: -0.1700
Data Index: 6361557 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.0615. Min Act: -0.1700
Data Index: 3317663 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.0927. Min Act: -0.1700
Data Index: 8677543 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3427. Min Range: -6.3427
Max Act: 6.0615. Min Act: -0.1700
Data Index: 4766689 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3427. Min Range: -6.3427
Max Act: 5.9677. Min Act: -0.1700
Data Index: 1639117 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3427. Min Range: -6.3427
Max Act: 5.9990. Min Act: -0.1700
Data Index: 8100967 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3427. Min Range: -6.3427
Max Act: 5.9990. Min Act: -0.1700
Data Index: 5888389 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3427. Min Range: -6.3427
Max Act: 5.9990. Min Act: -0.1700
Data Index: 5113123 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3427. Min Range: -6.3427
Max Act: 5.9990. Min Act: -0.1700
Data Index: 5116506 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3427. Min Range: -6.3427
Max Act: 5.9990. Min Act: -0.1700
Data Index: 4912736 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3427. Min Range: -6.3427
Max Act: 5.9677. Min Act: -0.1700
Data Index: 1263063 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3427. Min Range: -6.3427
Max Act: 5.9677. Min Act: -0.1700
Data Index: 538738 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19