Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3991. Min Range: -5.3991
Max Act: 5.3991. Min Act: -0.1700
Data Index: 8806120 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3991. Min Range: -5.3991
Max Act: 5.3366. Min Act: -0.1700
Data Index: 4781341 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3991. Min Range: -5.3991
Max Act: 5.2116. Min Act: -0.1700
Data Index: 8383810 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3991. Min Range: -5.3991
Max Act: 5.1491. Min Act: -0.1700
Data Index: 6222696 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.9929. Min Act: -0.1700
Data Index: 723097 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.8679. Min Act: -0.1700
Data Index: 1979205 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.8679. Min Act: -0.1700
Data Index: 699891 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.8366. Min Act: -0.1700
Data Index: 4218677 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.8054. Min Act: -0.1700
Data Index: 736571 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.8054. Min Act: -0.1700
Data Index: 3740917 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.8054. Min Act: -0.1700
Data Index: 397862 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.7741. Min Act: -0.1700
Data Index: 7894627 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.7741. Min Act: -0.1700
Data Index: 3902050 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.7741. Min Act: -0.1700
Data Index: 2106310 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.7741. Min Act: -0.1700
Data Index: 5570975 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.7429. Min Act: -0.1700
Data Index: 3567859 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.7116. Min Act: -0.1700
Data Index: 6776725 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.7429. Min Act: -0.1700
Data Index: 3350768 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.7429. Min Act: -0.1700
Data Index: 173613 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3991. Min Range: -5.3991
Max Act: 4.7429. Min Act: -0.1700
Data Index: 3482877 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19