Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2682 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.1489. Min Act: -0.1700
Data Index: 7517418 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9927. Min Act: -0.1700
Data Index: 7239038 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9614. Min Act: -0.1700
Data Index: 7365678 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9302. Min Act: -0.1700
Data Index: 6113656 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9302. Min Act: -0.1700
Data Index: 5786879 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 2647378 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 1602345 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 8398064 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 6375928 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 8117826 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 2961737 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 5519329 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8677. Min Act: -0.1700
Data Index: 320158 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8677. Min Act: -0.1700
Data Index: 2961736 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8989. Min Act: -0.1700
Data Index: 2878871 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8364. Min Act: -0.1700
Data Index: 2795259 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8677. Min Act: -0.1700
Data Index: 1629967 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8364. Min Act: -0.1700
Data Index: 3098177 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8052. Min Act: -0.1700
Data Index: 3283283 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8364. Min Act: -0.1700
Data Index: 6978878 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19