Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2837. Min Act: -0.1700
Data Index: 5243562 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2837. Min Act: -0.1700
Data Index: 4525508 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2052. Min Act: -0.1700
Data Index: 4513037 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2209. Min Act: -0.1700
Data Index: 6057405 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2209. Min Act: -0.1700
Data Index: 3541542 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2052. Min Act: -0.1700
Data Index: 8369217 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2209. Min Act: -0.1700
Data Index: 75775 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2052. Min Act: -0.1700
Data Index: 1989755 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2052. Min Act: -0.1700
Data Index: 3581043 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1894. Min Act: -0.1700
Data Index: 939004 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1422. Min Act: -0.1700
Data Index: 7494348 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1422. Min Act: -0.1700
Data Index: 7443025 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1422. Min Act: -0.1700
Data Index: 8728211 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1580. Min Act: -0.1700
Data Index: 8062176 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1422. Min Act: -0.1700
Data Index: 8010429 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1422. Min Act: -0.1700
Data Index: 5788322 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1265. Min Act: -0.1700
Data Index: 4802378 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1265. Min Act: -0.1700
Data Index: 2069808 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1107. Min Act: -0.1700
Data Index: 185629 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.1107. Min Act: -0.1700
Data Index: 6689762 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19