Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1036 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.4821. Min Act: -0.1700
Data Index: 6008700 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.4821. Min Act: -0.1700
Data Index: 8149981 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.4196. Min Act: -0.1700
Data Index: 6008695 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.4196. Min Act: -0.1700
Data Index: 8580314 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.3571. Min Act: -0.1700
Data Index: 7174414 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.3571. Min Act: -0.1700
Data Index: 295107 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.3571. Min Act: -0.1700
Data Index: 3107806 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.4196. Min Act: -0.1700
Data Index: 6327425 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.2946. Min Act: -0.1700
Data Index: 819151 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.2946. Min Act: -0.1700
Data Index: 2686259 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.2321. Min Act: -0.1700
Data Index: 4662289 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.2321. Min Act: -0.1700
Data Index: 2589695 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.2321. Min Act: -0.1700
Data Index: 7169495 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.2321. Min Act: -0.1700
Data Index: 7304248 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.1696. Min Act: -0.1700
Data Index: 1065378 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.2008. Min Act: -0.1700
Data Index: 3819955 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.1696. Min Act: -0.1700
Data Index: 8803532 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.1696. Min Act: -0.1700
Data Index: 5335062 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.1696. Min Act: -0.1700
Data Index: 1705602 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4821. Min Range: -8.4821
Max Act: 8.1383. Min Act: -0.1700
Data Index: 1242972 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19