Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 378 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.9251. Min Act: -0.1700
Data Index: 7650973 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.7064. Min Act: -0.1700
Data Index: 2807240 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.6439. Min Act: -0.1700
Data Index: 4465811 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.6439. Min Act: -0.1700
Data Index: 6628272 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.6126. Min Act: -0.1700
Data Index: 5447955 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.5814. Min Act: -0.1700
Data Index: 4430234 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.4876. Min Act: -0.1700
Data Index: 7947182 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.4564. Min Act: -0.1700
Data Index: 5996811 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.4564. Min Act: -0.1700
Data Index: 2004563 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.4251. Min Act: -0.1700
Data Index: 6029704 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.4251. Min Act: -0.1700
Data Index: 8622005 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.4251. Min Act: -0.1700
Data Index: 1143946 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.4251. Min Act: -0.1700
Data Index: 914351 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.4251. Min Act: -0.1700
Data Index: 8289073 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.3939. Min Act: -0.1700
Data Index: 4094085 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.3314. Min Act: -0.1700
Data Index: 6982673 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.3001. Min Act: -0.1700
Data Index: 993804 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.3314. Min Act: -0.1700
Data Index: 1226787 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.3001. Min Act: -0.1700
Data Index: 4964682 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9251. Min Range: -6.9251
Max Act: 6.3001. Min Act: -0.1700
Data Index: 5740053 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19