Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 918 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1062. Min Range: -6.1062
Max Act: 6.1062. Min Act: -0.1700
Data Index: 2608218 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1062. Min Range: -6.1062
Max Act: 6.0749. Min Act: -0.1700
Data Index: 1348810 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.8874. Min Act: -0.1700
Data Index: 916455 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.8874. Min Act: -0.1700
Data Index: 6252719 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.8874. Min Act: -0.1700
Data Index: 6936469 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.7624. Min Act: -0.1700
Data Index: 6970570 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.7624. Min Act: -0.1700
Data Index: 7210853 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.7312. Min Act: -0.1700
Data Index: 607886 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.6999. Min Act: -0.1700
Data Index: 5453870 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.6687. Min Act: -0.1700
Data Index: 6328093 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.6687. Min Act: -0.1700
Data Index: 3093398 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.6687. Min Act: -0.1700
Data Index: 8270732 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.6374. Min Act: -0.1700
Data Index: 162604 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.6062. Min Act: -0.1700
Data Index: 3338572 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.6062. Min Act: -0.1700
Data Index: 7611177 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.5749. Min Act: -0.1700
Data Index: 1604627 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.6062. Min Act: -0.1700
Data Index: 452426 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.5749. Min Act: -0.1700
Data Index: 4606297 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.5437. Min Act: -0.1700
Data Index: 6631425 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1062. Min Range: -6.1062
Max Act: 5.5437. Min Act: -0.1700
Data Index: 3911867 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19