Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2417. Min Range: -6.2417
Max Act: 6.2417. Min Act: -0.1700
Data Index: 4391137 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2417. Min Range: -6.2417
Max Act: 6.0542. Min Act: -0.1700
Data Index: 7965864 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2417. Min Range: -6.2417
Max Act: 6.0230. Min Act: -0.1700
Data Index: 2790045 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2417. Min Range: -6.2417
Max Act: 6.0230. Min Act: -0.1700
Data Index: 4112825 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.9292. Min Act: -0.1700
Data Index: 2614499 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.9292. Min Act: -0.1700
Data Index: 2528286 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.8980. Min Act: -0.1700
Data Index: 8012898 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.8980. Min Act: -0.1700
Data Index: 4593734 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.8980. Min Act: -0.1700
Data Index: 5020771 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.8667. Min Act: -0.1700
Data Index: 561960 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.8042. Min Act: -0.1700
Data Index: 8565587 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.8042. Min Act: -0.1700
Data Index: 944899 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.8042. Min Act: -0.1700
Data Index: 75898 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.8042. Min Act: -0.1700
Data Index: 5983553 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.8042. Min Act: -0.1700
Data Index: 6594766 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.7730. Min Act: -0.1700
Data Index: 670148 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.7730. Min Act: -0.1700
Data Index: 6848316 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.7730. Min Act: -0.1700
Data Index: 4080193 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.7730. Min Act: -0.1700
Data Index: 4959939 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2417. Min Range: -6.2417
Max Act: 5.7730. Min Act: -0.1700
Data Index: 5130138 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19