Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 469 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.7345. Min Act: -0.1700
Data Index: 3501956 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.6095. Min Act: -0.1700
Data Index: 4245848 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.5782. Min Act: -0.1700
Data Index: 3533359 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.5470. Min Act: -0.1700
Data Index: 2275668 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.5157. Min Act: -0.1700
Data Index: 2675848 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.4845. Min Act: -0.1700
Data Index: 8166882 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.4845. Min Act: -0.1700
Data Index: 8560561 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.4532. Min Act: -0.1700
Data Index: 5601410 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.4532. Min Act: -0.1700
Data Index: 854859 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.4532. Min Act: -0.1700
Data Index: 4188563 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.4532. Min Act: -0.1700
Data Index: 1235315 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.4220. Min Act: -0.1700
Data Index: 1565108 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.4220. Min Act: -0.1700
Data Index: 1656936 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.3907. Min Act: -0.1700
Data Index: 3045905 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.3907. Min Act: -0.1700
Data Index: 4348533 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.3907. Min Act: -0.1700
Data Index: 4219088 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.3907. Min Act: -0.1700
Data Index: 3601915 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.3907. Min Act: -0.1700
Data Index: 6997820 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.3595. Min Act: -0.1700
Data Index: 861970 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7345. Min Range: -4.7345
Max Act: 4.3595. Min Act: -0.1700
Data Index: 5390390 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19