Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.2683. Min Act: -0.1700
Data Index: 3419716 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0183. Min Act: -0.1700
Data Index: 2358141 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.9871. Min Act: -0.1700
Data Index: 7156262 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.9246. Min Act: -0.1700
Data Index: 473275 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.8621. Min Act: -0.1700
Data Index: 6078449 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.8621. Min Act: -0.1700
Data Index: 346211 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.8621. Min Act: -0.1700
Data Index: 7820828 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.7996. Min Act: -0.1700
Data Index: 7664938 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.7371. Min Act: -0.1700
Data Index: 4430787 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.7371. Min Act: -0.1700
Data Index: 4306514 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.7371. Min Act: -0.1700
Data Index: 934982 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.7371. Min Act: -0.1700
Data Index: 7267243 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.7058. Min Act: -0.1700
Data Index: 6062955 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.7058. Min Act: -0.1700
Data Index: 7313214 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.6746. Min Act: -0.1700
Data Index: 2152974 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.6746. Min Act: -0.1700
Data Index: 7414602 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.6433. Min Act: -0.1700
Data Index: 3852378 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.6433. Min Act: -0.1700
Data Index: 4559531 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.6121. Min Act: -0.1700
Data Index: 5311632 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2683. Min Range: -5.2683
Max Act: 4.6433. Min Act: -0.1700
Data Index: 2358142 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19