Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.3503. Min Act: -0.1700
Data Index: 8042701 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.3190. Min Act: -0.1700
Data Index: 3980160 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1940. Min Act: -0.1700
Data Index: 1924493 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1628. Min Act: -0.1700
Data Index: 968317 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1628. Min Act: -0.1700
Data Index: 5667522 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1628. Min Act: -0.1700
Data Index: 5344400 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1628. Min Act: -0.1700
Data Index: 8439541 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1315. Min Act: -0.1700
Data Index: 3980163 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1315. Min Act: -0.1700
Data Index: 8439539 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1315. Min Act: -0.1700
Data Index: 1973692 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1315. Min Act: -0.1700
Data Index: 1113856 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1315. Min Act: -0.1700
Data Index: 6120230 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1315. Min Act: -0.1700
Data Index: 6434586 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1315. Min Act: -0.1700
Data Index: 7758282 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1003. Min Act: -0.1700
Data Index: 3721075 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1003. Min Act: -0.1700
Data Index: 8140361 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1003. Min Act: -0.1700
Data Index: 6538523 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1003. Min Act: -0.1699
Data Index: 3782920 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1003. Min Act: -0.1700
Data Index: 1924488 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3503. Min Range: -6.3503
Max Act: 6.1003. Min Act: -0.1700
Data Index: 2026877 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19