Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4369 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.8754. Min Act: -0.1700
Data Index: 3652620 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.8129. Min Act: -0.1700
Data Index: 3644369 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.8129. Min Act: -0.1700
Data Index: 8080206 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6879. Min Act: -0.1700
Data Index: 61314 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6879. Min Act: -0.1700
Data Index: 5544203 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6879. Min Act: -0.1700
Data Index: 359729 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6566. Min Act: -0.1700
Data Index: 3659521 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6566. Min Act: -0.1700
Data Index: 7261619 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6254. Min Act: -0.1700
Data Index: 816843 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6254. Min Act: -0.1700
Data Index: 1578173 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6254. Min Act: -0.1700
Data Index: 8435702 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.6254. Min Act: -0.1700
Data Index: 3981985 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5941. Min Act: -0.1700
Data Index: 1215955 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5941. Min Act: -0.1700
Data Index: 1215956 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5941. Min Act: -0.1700
Data Index: 5544205 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5941. Min Act: -0.1700
Data Index: 6545209 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5629. Min Act: -0.1700
Data Index: 6167576 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5629. Min Act: -0.1700
Data Index: 8435701 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5629. Min Act: -0.1700
Data Index: 3565275 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8754. Min Range: -4.8754
Max Act: 4.5629. Min Act: -0.1700
Data Index: 2902037 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19