Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4250 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0238. Min Range: -4.0238
Max Act: 4.0238. Min Act: -0.1700
Data Index: 6119754 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.9300. Min Act: -0.1700
Data Index: 5961353 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.9300. Min Act: -0.1700
Data Index: 1859309 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.8988. Min Act: -0.1700
Data Index: 6956576 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.8519. Min Act: -0.1700
Data Index: 8350286 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.8362. Min Act: -0.1700
Data Index: 4081932 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.7737. Min Act: -0.1700
Data Index: 969846 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.7893. Min Act: -0.1700
Data Index: 3628937 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.7737. Min Act: -0.1700
Data Index: 3976446 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.7111. Min Act: -0.1700
Data Index: 415218 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.7111. Min Act: -0.1700
Data Index: 3825657 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.7111. Min Act: -0.1700
Data Index: 5652777 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.7111. Min Act: -0.1700
Data Index: 8021637 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.7111. Min Act: -0.1700
Data Index: 2962741 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.7111. Min Act: -0.1700
Data Index: 6797184 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.6798. Min Act: -0.1700
Data Index: 89737 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.6642. Min Act: -0.1700
Data Index: 4980097 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.6798. Min Act: -0.1700
Data Index: 7491229 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.6798. Min Act: -0.1700
Data Index: 7457789 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0238. Min Range: -4.0238
Max Act: 3.6642. Min Act: -0.1700
Data Index: 3762769 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19