Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.9539. Min Act: -0.1700
Data Index: 5401726 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.7039. Min Act: -0.1700
Data Index: 3400949 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.6414. Min Act: -0.1700
Data Index: 8151436 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.3914. Min Act: -0.1700
Data Index: 7996032 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.3289. Min Act: -0.1700
Data Index: 5490935 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.2039. Min Act: -0.1700
Data Index: 1987326 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.2664. Min Act: -0.1700
Data Index: 6847062 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.2039. Min Act: -0.1700
Data Index: 7792083 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.2039. Min Act: -0.1700
Data Index: 186143 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.1414. Min Act: -0.1700
Data Index: 6848299 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.0789. Min Act: -0.1700
Data Index: 1020108 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.0789. Min Act: -0.1700
Data Index: 7246810 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.1414. Min Act: -0.1700
Data Index: 5375155 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.0164. Min Act: -0.1700
Data Index: 4109128 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.0164. Min Act: -0.1700
Data Index: 5152819 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9539. Min Range: -8.9539
Max Act: 8.0164. Min Act: -0.1700
Data Index: 5475851 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9539. Min Range: -8.9539
Max Act: 7.9539. Min Act: -0.1700
Data Index: 1281077 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9539. Min Range: -8.9539
Max Act: 7.9539. Min Act: -0.1700
Data Index: 2120031 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9539. Min Range: -8.9539
Max Act: 7.8914. Min Act: -0.1700
Data Index: 2709052 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9539. Min Range: -8.9539
Max Act: 7.8914. Min Act: -0.1700
Data Index: 3136367 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19