Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4924 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.7220. Min Act: -0.1700
Data Index: 3000450 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.3783. Min Act: -0.1700
Data Index: 3814302 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.4095. Min Act: -0.1700
Data Index: 6503371 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.3470. Min Act: -0.1700
Data Index: 1275221 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.3470. Min Act: -0.1700
Data Index: 6503370 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.3158. Min Act: -0.1700
Data Index: 5232798 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.2845. Min Act: -0.1700
Data Index: 2440077 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.2845. Min Act: -0.1700
Data Index: 2134605 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.2845. Min Act: -0.1700
Data Index: 1314357 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.2845. Min Act: -0.1700
Data Index: 4809555 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.2533. Min Act: -0.1700
Data Index: 4364730 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.2220. Min Act: -0.1700
Data Index: 5480749 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.2220. Min Act: -0.1700
Data Index: 454506 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.1595. Min Act: -0.1700
Data Index: 7452477 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.1908. Min Act: -0.1700
Data Index: 625999 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.1595. Min Act: -0.1700
Data Index: 5725920 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.1283. Min Act: -0.1700
Data Index: 5299564 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.1595. Min Act: -0.1700
Data Index: 333680 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.1595. Min Act: -0.1700
Data Index: 8660878 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7220. Min Range: -7.7220
Max Act: 7.1595. Min Act: -0.1700
Data Index: 4064667 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19