Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3777. Min Range: -5.3777
Max Act: 5.3777. Min Act: -0.1700
Data Index: 5174258 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3777. Min Range: -5.3777
Max Act: 5.2839. Min Act: -0.1700
Data Index: 3308250 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3777. Min Range: -5.3777
Max Act: 5.1277. Min Act: -0.1700
Data Index: 6648071 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3777. Min Range: -5.3777
Max Act: 5.0964. Min Act: -0.1700
Data Index: 4080500 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3777. Min Range: -5.3777
Max Act: 5.0964. Min Act: -0.1700
Data Index: 6870437 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3777. Min Range: -5.3777
Max Act: 5.0652. Min Act: -0.1700
Data Index: 3422778 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3777. Min Range: -5.3777
Max Act: 5.0339. Min Act: -0.1700
Data Index: 8581573 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3777. Min Range: -5.3777
Max Act: 5.0339. Min Act: -0.1700
Data Index: 4080499 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.9402. Min Act: -0.1700
Data Index: 5906124 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.9402. Min Act: -0.1700
Data Index: 6870440 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.9089. Min Act: -0.1700
Data Index: 8115620 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.8464. Min Act: -0.1700
Data Index: 6256003 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.8152. Min Act: -0.1700
Data Index: 907663 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.8152. Min Act: -0.1700
Data Index: 6909330 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.8152. Min Act: -0.1700
Data Index: 886974 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.8152. Min Act: -0.1700
Data Index: 7811652 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.7839. Min Act: -0.1700
Data Index: 5906125 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.7839. Min Act: -0.1700
Data Index: 6646813 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.7839. Min Act: -0.1700
Data Index: 8255861 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3777. Min Range: -5.3777
Max Act: 4.7527. Min Act: -0.1700
Data Index: 4399938 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19