Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2241. Min Range: -4.2241
Max Act: 4.2241. Min Act: -0.1700
Data Index: 7953780 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2241. Min Range: -4.2241
Max Act: 4.0678. Min Act: -0.1700
Data Index: 871024 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2241. Min Range: -4.2241
Max Act: 4.0053. Min Act: -0.1700
Data Index: 6352663 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.9427. Min Act: -0.1700
Data Index: 2795295 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.9115. Min Act: -0.1700
Data Index: 33349 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.9427. Min Act: -0.1700
Data Index: 3052700 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.9427. Min Act: -0.1700
Data Index: 4238830 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.9115. Min Act: -0.1700
Data Index: 5303351 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.9115. Min Act: -0.1700
Data Index: 360190 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.8802. Min Act: -0.1700
Data Index: 2153851 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.8489. Min Act: -0.1700
Data Index: 75300 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.8802. Min Act: -0.1700
Data Index: 5444454 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.8489. Min Act: -0.1700
Data Index: 4048251 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.8489. Min Act: -0.1700
Data Index: 6606860 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.8177. Min Act: -0.1700
Data Index: 5908975 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.8177. Min Act: -0.1700
Data Index: 1719461 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.8177. Min Act: -0.1700
Data Index: 5488375 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.8177. Min Act: -0.1700
Data Index: 3237233 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.7864. Min Act: -0.1700
Data Index: 2584168 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2241. Min Range: -4.2241
Max Act: 3.7551. Min Act: -0.1700
Data Index: 5380198 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19