Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4995 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.8124. Min Act: -0.1700
Data Index: 1084228 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.7811. Min Act: -0.1700
Data Index: 30218 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.7811. Min Act: -0.1700
Data Index: 4628777 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.7499. Min Act: -0.1700
Data Index: 2334106 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.7186. Min Act: -0.1700
Data Index: 503894 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.6249. Min Act: -0.1700
Data Index: 5065004 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.6249. Min Act: -0.1700
Data Index: 801273 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.5936. Min Act: -0.1700
Data Index: 2276575 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.5936. Min Act: -0.1700
Data Index: 1585942 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.5936. Min Act: -0.1700
Data Index: 2714928 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.5624. Min Act: -0.1700
Data Index: 6555390 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.5624. Min Act: -0.1700
Data Index: 1120314 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.5624. Min Act: -0.1700
Data Index: 6705466 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.5311. Min Act: -0.1700
Data Index: 2268041 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.5311. Min Act: -0.1700
Data Index: 7470180 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.5311. Min Act: -0.1700
Data Index: 2448559 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.4999. Min Act: -0.1700
Data Index: 7174262 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.4686. Min Act: -0.1700
Data Index: 940556 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.4374. Min Act: -0.1700
Data Index: 935268 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8124. Min Range: -5.8124
Max Act: 5.4374. Min Act: -0.1700
Data Index: 5472267 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19