Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.5637. Min Act: -0.1700
Data Index: 2342090 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.5325. Min Act: -0.1700
Data Index: 1622764 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.5012. Min Act: -0.1700
Data Index: 2877311 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.4387. Min Act: -0.1700
Data Index: 2788408 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.4387. Min Act: -0.1700
Data Index: 459215 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.4387. Min Act: -0.1700
Data Index: 1059623 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.4075. Min Act: -0.1700
Data Index: 1768843 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.4075. Min Act: -0.1700
Data Index: 6931185 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.3450. Min Act: -0.1700
Data Index: 7113775 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.3450. Min Act: -0.1700
Data Index: 552052 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.3137. Min Act: -0.1700
Data Index: 4784401 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.3450. Min Act: -0.1700
Data Index: 7261943 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.3137. Min Act: -0.1700
Data Index: 53757 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.3137. Min Act: -0.1700
Data Index: 101644 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.2825. Min Act: -0.1700
Data Index: 2484399 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.2825. Min Act: -0.1700
Data Index: 415532 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.2825. Min Act: -0.1700
Data Index: 6153535 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.2512. Min Act: -0.1700
Data Index: 6983229 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.2512. Min Act: -0.1700
Data Index: 51921 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5637. Min Range: -6.5637
Max Act: 6.2825. Min Act: -0.1700
Data Index: 6783664 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19