Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4524 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.7067. Min Act: -0.1700
Data Index: 1565972 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.4254. Min Act: -0.1700
Data Index: 1876928 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.3317. Min Act: -0.1700
Data Index: 4224233 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.3317. Min Act: -0.1700
Data Index: 4937824 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.3004. Min Act: -0.1700
Data Index: 2477827 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.2692. Min Act: -0.1700
Data Index: 5200263 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.3004. Min Act: -0.1700
Data Index: 5661952 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.2067. Min Act: -0.1700
Data Index: 5778746 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.1442. Min Act: -0.1700
Data Index: 4283670 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.0817. Min Act: -0.1700
Data Index: 4823440 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.1129. Min Act: -0.1700
Data Index: 203519 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.0817. Min Act: -0.1700
Data Index: 595651 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7067. Min Range: -6.7067
Max Act: 6.0817. Min Act: -0.1700
Data Index: 7154771 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7067. Min Range: -6.7067
Max Act: 5.9879. Min Act: -0.1700
Data Index: 4497926 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7067. Min Range: -6.7067
Max Act: 5.9879. Min Act: -0.1700
Data Index: 1530269 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7067. Min Range: -6.7067
Max Act: 5.9879. Min Act: -0.1700
Data Index: 8227965 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7067. Min Range: -6.7067
Max Act: 5.9567. Min Act: -0.1700
Data Index: 2701266 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7067. Min Range: -6.7067
Max Act: 5.8942. Min Act: -0.1700
Data Index: 664595 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7067. Min Range: -6.7067
Max Act: 5.8942. Min Act: -0.1700
Data Index: 567139 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7067. Min Range: -6.7067
Max Act: 5.8629. Min Act: -0.1700
Data Index: 3648154 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19