Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.8257. Min Act: -0.1700
Data Index: 4989629 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.8257. Min Act: -0.1700
Data Index: 6256729 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.8570. Min Act: -0.1700
Data Index: 3621787 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.7945. Min Act: -0.1700
Data Index: 4222769 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.6695. Min Act: -0.1700
Data Index: 3596364 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.6695. Min Act: -0.1700
Data Index: 8681994 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.6382. Min Act: -0.1700
Data Index: 5046116 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.6382. Min Act: -0.1700
Data Index: 679527 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.6382. Min Act: -0.1700
Data Index: 3575431 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.5445. Min Act: -0.1700
Data Index: 4787654 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.5445. Min Act: -0.1700
Data Index: 8106404 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.5132. Min Act: -0.1700
Data Index: 1762201 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.5132. Min Act: -0.1700
Data Index: 7003616 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.4820. Min Act: -0.1700
Data Index: 8420091 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.4820. Min Act: -0.1700
Data Index: 675666 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.4820. Min Act: -0.1700
Data Index: 7301770 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.4195. Min Act: -0.1700
Data Index: 8310664 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.4507. Min Act: -0.1700
Data Index: 6755059 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.4507. Min Act: -0.1700
Data Index: 4394993 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8570. Min Range: -6.8570
Max Act: 6.4507. Min Act: -0.1700
Data Index: 7152421 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19