Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2881 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.6866. Min Act: -0.1700
Data Index: 2800549 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.5304. Min Act: -0.1700
Data Index: 7638167 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.4679. Min Act: -0.1700
Data Index: 5074637 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.4991. Min Act: -0.1700
Data Index: 4195921 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.4366. Min Act: -0.1700
Data Index: 5024163 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.4054. Min Act: -0.1700
Data Index: 4827364 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.2491. Min Act: -0.1700
Data Index: 2976124 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.1554. Min Act: -0.1700
Data Index: 7454510 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.1554. Min Act: -0.1700
Data Index: 1082659 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.1241. Min Act: -0.1700
Data Index: 1598148 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.1241. Min Act: -0.1700
Data Index: 5047151 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.1554. Min Act: -0.1700
Data Index: 4225568 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.0929. Min Act: -0.1700
Data Index: 4657799 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.0929. Min Act: -0.1700
Data Index: 2978862 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.0929. Min Act: -0.1700
Data Index: 1214795 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.0929. Min Act: -0.1700
Data Index: 1669407 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.0616. Min Act: -0.1700
Data Index: 1791289 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.0616. Min Act: -0.1700
Data Index: 2249501 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.1241. Min Act: -0.1700
Data Index: 7157443 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6866. Min Range: -5.6866
Max Act: 5.0304. Min Act: -0.1700
Data Index: 2065322 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19