Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.9489. Min Act: -0.1700
Data Index: 6163639 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.9176. Min Act: -0.1700
Data Index: 82222 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.8551. Min Act: -0.1700
Data Index: 7941272 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.8239. Min Act: -0.1700
Data Index: 1974398 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.8239. Min Act: -0.1700
Data Index: 8128098 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.7926. Min Act: -0.1700
Data Index: 6361560 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.7301. Min Act: -0.1700
Data Index: 6396418 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6676. Min Act: -0.1700
Data Index: 5181723 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6676. Min Act: -0.1700
Data Index: 251339 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6676. Min Act: -0.1700
Data Index: 3712513 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6676. Min Act: -0.1700
Data Index: 203320 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6676. Min Act: -0.1700
Data Index: 190577 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6364. Min Act: -0.1700
Data Index: 5032158 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6364. Min Act: -0.1700
Data Index: 1441486 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6364. Min Act: -0.1700
Data Index: 4793043 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6364. Min Act: -0.1700
Data Index: 2626556 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6051. Min Act: -0.1700
Data Index: 8096646 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6051. Min Act: -0.1700
Data Index: 7730598 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.5739. Min Act: -0.1700
Data Index: 7575737 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9489. Min Range: -5.9489
Max Act: 5.6364. Min Act: -0.1700
Data Index: 7784757 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19