Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1970 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.6986. Min Act: -0.1700
Data Index: 7674051 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.6674. Min Act: -0.1700
Data Index: 7597740 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.6674. Min Act: -0.1700
Data Index: 2621849 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.3236. Min Act: -0.1700
Data Index: 1078558 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.2924. Min Act: -0.1700
Data Index: 8470329 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.1986. Min Act: -0.1700
Data Index: 779804 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.1674. Min Act: -0.1700
Data Index: 1865913 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.1361. Min Act: -0.1700
Data Index: 1556922 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.0736. Min Act: -0.1700
Data Index: 709661 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.0424. Min Act: -0.1700
Data Index: 3245134 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.0424. Min Act: -0.1700
Data Index: 8131932 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.0736. Min Act: -0.1700
Data Index: 8065337 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6986. Min Range: -6.6986
Max Act: 6.0424. Min Act: -0.1700
Data Index: 1411664 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6986. Min Range: -6.6986
Max Act: 5.9486. Min Act: -0.1700
Data Index: 3439598 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6986. Min Range: -6.6986
Max Act: 5.9486. Min Act: -0.1700
Data Index: 4412877 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6986. Min Range: -6.6986
Max Act: 5.9486. Min Act: -0.1700
Data Index: 1664048 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6986. Min Range: -6.6986
Max Act: 5.9486. Min Act: -0.1700
Data Index: 7995782 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6986. Min Range: -6.6986
Max Act: 5.9174. Min Act: -0.1700
Data Index: 5339115 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6986. Min Range: -6.6986
Max Act: 5.9174. Min Act: -0.1700
Data Index: 7734034 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6986. Min Range: -6.6986
Max Act: 5.8861. Min Act: -0.1700
Data Index: 6643827 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19