Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5360 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1664. Min Range: -3.1664
Max Act: 3.1664. Min Act: -0.1700
Data Index: 5612394 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1664. Min Range: -3.1664
Max Act: 3.0403. Min Act: -0.1700
Data Index: 1125052 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1664. Min Range: -3.1664
Max Act: 3.0088. Min Act: -0.1700
Data Index: 3273440 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9929. Min Act: -0.1700
Data Index: 3887979 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9929. Min Act: -0.1700
Data Index: 3887981 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9771. Min Act: -0.1700
Data Index: 634293 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9613. Min Act: -0.1700
Data Index: 4572893 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9455. Min Act: -0.1700
Data Index: 4554503 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9455. Min Act: -0.1700
Data Index: 927987 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9455. Min Act: -0.1700
Data Index: 2475481 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9455. Min Act: -0.1700
Data Index: 3273444 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9297. Min Act: -0.1700
Data Index: 2366589 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9297. Min Act: -0.1700
Data Index: 1150085 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9455. Min Act: -0.1700
Data Index: 1444476 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9138. Min Act: -0.1700
Data Index: 5251270 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.8980. Min Act: -0.1700
Data Index: 5892738 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.8980. Min Act: -0.1700
Data Index: 7780931 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9138. Min Act: -0.1700
Data Index: 6661086 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9138. Min Act: -0.1700
Data Index: 3410654 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1664. Min Range: -3.1664
Max Act: 2.9138. Min Act: -0.1700
Data Index: 8038158 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19