Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5746 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.1522. Min Act: -0.1700
Data Index: 1063731 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.1210. Min Act: -0.1700
Data Index: 6617193 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0272. Min Act: -0.1700
Data Index: 5040384 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0584. Min Act: -0.1700
Data Index: 4962358 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0272. Min Act: -0.1700
Data Index: 4405763 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0272. Min Act: -0.1700
Data Index: 7839594 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0584. Min Act: -0.1700
Data Index: 7373787 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9959. Min Act: -0.1700
Data Index: 5869168 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9959. Min Act: -0.1700
Data Index: 4350445 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9959. Min Act: -0.1700
Data Index: 1574987 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9959. Min Act: -0.1700
Data Index: 2935993 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9959. Min Act: -0.1700
Data Index: 6623470 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9959. Min Act: -0.1700
Data Index: 5117108 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9959. Min Act: -0.1700
Data Index: 970654 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9959. Min Act: -0.1700
Data Index: 5948364 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9647. Min Act: -0.1700
Data Index: 5157512 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9647. Min Act: -0.1700
Data Index: 1046865 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9647. Min Act: -0.1700
Data Index: 1347949 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9647. Min Act: -0.1700
Data Index: 499986 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9021. Min Act: -0.1700
Data Index: 3355817 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19