Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5149 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.9234. Min Act: -0.1700
Data Index: 6643132 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.8609. Min Act: -0.1700
Data Index: 8487527 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.8296. Min Act: -0.1700
Data Index: 1888265 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.7984. Min Act: -0.1700
Data Index: 6424381 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.7671. Min Act: -0.1700
Data Index: 8297264 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.7671. Min Act: -0.1700
Data Index: 1857585 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.7359. Min Act: -0.1700
Data Index: 448616 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.7046. Min Act: -0.1700
Data Index: 1237794 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.7046. Min Act: -0.1700
Data Index: 6802066 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.7046. Min Act: -0.1700
Data Index: 1189765 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.7046. Min Act: -0.1700
Data Index: 1125985 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.6734. Min Act: -0.1700
Data Index: 2486678 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.6734. Min Act: -0.1700
Data Index: 5942290 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.6734. Min Act: -0.1700
Data Index: 2857230 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.6421. Min Act: -0.1700
Data Index: 5736494 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.6109. Min Act: -0.1700
Data Index: 5304983 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.6109. Min Act: -0.1700
Data Index: 2040634 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.6421. Min Act: -0.1700
Data Index: 6146235 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.6109. Min Act: -0.1700
Data Index: 6731074 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9234. Min Range: -5.9234
Max Act: 5.6109. Min Act: -0.1700
Data Index: 5430031 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19