Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4276 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.1664. Min Act: -0.1700
Data Index: 8260462 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0726. Min Act: -0.1700
Data Index: 170622 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0726. Min Act: -0.1700
Data Index: 6946712 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0101. Min Act: -0.1700
Data Index: 1191877 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0101. Min Act: -0.1700
Data Index: 1583378 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.9476. Min Act: -0.1700
Data Index: 4693913 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.9164. Min Act: -0.1700
Data Index: 5196479 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.8851. Min Act: -0.1700
Data Index: 4268261 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.8851. Min Act: -0.1700
Data Index: 4632178 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.8226. Min Act: -0.1700
Data Index: 3093690 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.7914. Min Act: -0.1700
Data Index: 5244034 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.8226. Min Act: -0.1700
Data Index: 7790589 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.8226. Min Act: -0.1700
Data Index: 3800013 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.7914. Min Act: -0.1700
Data Index: 1716694 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.7914. Min Act: -0.1700
Data Index: 5067238 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.7914. Min Act: -0.1700
Data Index: 8368637 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.7601. Min Act: -0.1700
Data Index: 8033698 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.7601. Min Act: -0.1700
Data Index: 1011698 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.7601. Min Act: -0.1700
Data Index: 7323900 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1664. Min Range: -5.1664
Max Act: 4.7289. Min Act: -0.1700
Data Index: 7572868 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19