Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4875 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.7096. Min Act: -0.1700
Data Index: 7851198 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.6783. Min Act: -0.1700
Data Index: 296319 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.6158. Min Act: -0.1700
Data Index: 4962443 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.5533. Min Act: -0.1700
Data Index: 5126743 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.4283. Min Act: -0.1700
Data Index: 2248188 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.3971. Min Act: -0.1700
Data Index: 7125082 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.3971. Min Act: -0.1700
Data Index: 4188744 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.3658. Min Act: -0.1700
Data Index: 8500528 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.3658. Min Act: -0.1700
Data Index: 6168177 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.3346. Min Act: -0.1700
Data Index: 7746982 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.3346. Min Act: -0.1700
Data Index: 6438467 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.2721. Min Act: -0.1700
Data Index: 1931013 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.2721. Min Act: -0.1700
Data Index: 6500367 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.2721. Min Act: -0.1700
Data Index: 507347 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.2408. Min Act: -0.1700
Data Index: 8697303 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.2408. Min Act: -0.1700
Data Index: 1043951 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.2096. Min Act: -0.1700
Data Index: 3277669 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.1783. Min Act: -0.1700
Data Index: 5535815 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.1783. Min Act: -0.1700
Data Index: 6318979 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7096. Min Range: -6.7096
Max Act: 6.1471. Min Act: -0.1700
Data Index: 8691956 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19