Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1847 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1132. Min Range: -5.1132
Max Act: 5.1132. Min Act: -0.1700
Data Index: 4175374 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.9882. Min Act: -0.1700
Data Index: 3005034 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.9882. Min Act: -0.1700
Data Index: 7243467 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.9882. Min Act: -0.1700
Data Index: 5406872 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.9257. Min Act: -0.1700
Data Index: 8730549 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.9257. Min Act: -0.1700
Data Index: 7402349 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8945. Min Act: -0.1700
Data Index: 3894858 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8945. Min Act: -0.1700
Data Index: 5057346 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8945. Min Act: -0.1700
Data Index: 7535820 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 1664888 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 8226124 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 2362669 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 5173631 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 5858612 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 5732260 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8945. Min Act: -0.1700
Data Index: 4014325 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8320. Min Act: -0.1700
Data Index: 2314724 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8320. Min Act: -0.1700
Data Index: 3658277 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8320. Min Act: -0.1700
Data Index: 792016 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1132. Min Range: -5.1132
Max Act: 4.8007. Min Act: -0.1700
Data Index: 706378 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19