Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2227 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.6391. Min Act: -0.1700
Data Index: 8474675 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.3891. Min Act: -0.1700
Data Index: 1891683 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.2328. Min Act: -0.1700
Data Index: 5596301 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.2016. Min Act: -0.1700
Data Index: 2445707 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.2016. Min Act: -0.1700
Data Index: 2387968 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1391. Min Act: -0.1700
Data Index: 1511144 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1703. Min Act: -0.1700
Data Index: 6207563 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1391. Min Act: -0.1700
Data Index: 3463914 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1391. Min Act: -0.1700
Data Index: 2009154 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1078. Min Act: -0.1700
Data Index: 5535927 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1078. Min Act: -0.1700
Data Index: 2468086 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1078. Min Act: -0.1700
Data Index: 2928656 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1391. Min Act: -0.1700
Data Index: 718646 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1078. Min Act: -0.1700
Data Index: 1249604 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1078. Min Act: -0.1700
Data Index: 8492058 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1078. Min Act: -0.1700
Data Index: 4008115 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1078. Min Act: -0.1700
Data Index: 2962718 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.1078. Min Act: -0.1700
Data Index: 1735740 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.0766. Min Act: -0.1700
Data Index: 4008113 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6391. Min Range: -5.6391
Max Act: 5.0766. Min Act: -0.1700
Data Index: 515300 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19