Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2235. Min Range: -4.2235
Max Act: 4.2235. Min Act: -0.1694
Data Index: 88904 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2235. Min Range: -4.2235
Max Act: 4.1923. Min Act: -0.1699
Data Index: 88905 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2235. Min Range: -4.2235
Max Act: 3.8328. Min Act: -0.1699
Data Index: 88903 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2235. Min Range: -4.2235
Max Act: 3.6294. Min Act: -0.1700
Data Index: 5840513 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2235. Min Range: -4.2235
Max Act: 3.3631. Min Act: -0.1627
Data Index: 26366 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2235. Min Range: -4.2235
Max Act: 3.0328. Min Act: -0.1700
Data Index: 5840512 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2235. Min Range: -4.2235
Max Act: 3.0170. Min Act: -0.1700
Data Index: 5840514 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.9538. Min Act: -0.1696
Data Index: 566013 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.5223. Min Act: -0.1685
Data Index: 1555272 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.4737. Min Act: -0.1698
Data Index: 3620514 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.4737. Min Act: -0.1700
Data Index: 5552173 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.4574. Min Act: -0.1698
Data Index: 5026121 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.4574. Min Act: -0.1700
Data Index: 4890017 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.3923. Min Act: -0.1700
Data Index: 7538243 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.3759. Min Act: -0.1700
Data Index: 4225653 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.2939. Min Act: -0.1700
Data Index: 5482349 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.2939. Min Act: -0.1700
Data Index: 8131960 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.2774. Min Act: -0.1700
Data Index: 1153156 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.2609. Min Act: -0.1694
Data Index: 4290260 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2235. Min Range: -4.2235
Max Act: 2.2774. Min Act: -0.1685
Data Index: 8644267 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19