Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6831. Min Range: -7.6831
Max Act: 7.6831. Min Act: -0.1700
Data Index: 2595897 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6831. Min Range: -7.6831
Max Act: 7.2456. Min Act: -0.1700
Data Index: 5322053 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6831. Min Range: -7.6831
Max Act: 7.1831. Min Act: -0.1700
Data Index: 3531889 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6831. Min Range: -7.6831
Max Act: 7.1206. Min Act: -0.1700
Data Index: 7329630 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6831. Min Range: -7.6831
Max Act: 7.0581. Min Act: -0.1700
Data Index: 7030040 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.9956. Min Act: -0.1700
Data Index: 2342736 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.9643. Min Act: -0.1700
Data Index: 1562229 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.9643. Min Act: -0.1700
Data Index: 4110559 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.9331. Min Act: -0.1700
Data Index: 7617955 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.9331. Min Act: -0.1700
Data Index: 3801552 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.8706. Min Act: -0.1700
Data Index: 5524962 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.8393. Min Act: -0.1700
Data Index: 8305191 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.8081. Min Act: -0.1700
Data Index: 5000458 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.7768. Min Act: -0.1700
Data Index: 970305 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.8081. Min Act: -0.1700
Data Index: 1194379 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.7768. Min Act: -0.1700
Data Index: 1753984 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.7768. Min Act: -0.1700
Data Index: 7707306 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.7456. Min Act: -0.1700
Data Index: 1371986 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.7143. Min Act: -0.1700
Data Index: 8173108 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6831. Min Range: -7.6831
Max Act: 6.6831. Min Act: -0.1700
Data Index: 8074664 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19