Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 920 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7118. Min Range: -6.7118
Max Act: 6.7118. Min Act: -0.1700
Data Index: 3895883 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7118. Min Range: -6.7118
Max Act: 6.4618. Min Act: -0.1700
Data Index: 6123736 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7118. Min Range: -6.7118
Max Act: 6.3056. Min Act: -0.1700
Data Index: 7330215 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7118. Min Range: -6.7118
Max Act: 6.1181. Min Act: -0.1700
Data Index: 8257174 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7118. Min Range: -6.7118
Max Act: 6.0556. Min Act: -0.1700
Data Index: 4591578 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.8993. Min Act: -0.1700
Data Index: 4663685 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.8681. Min Act: -0.1700
Data Index: 2174886 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.8681. Min Act: -0.1700
Data Index: 5096342 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.8056. Min Act: -0.1700
Data Index: 2318518 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7743. Min Act: -0.1700
Data Index: 349652 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7743. Min Act: -0.1700
Data Index: 975579 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7743. Min Act: -0.1700
Data Index: 6442159 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7431. Min Act: -0.1700
Data Index: 4542327 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7118. Min Act: -0.1700
Data Index: 5121178 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7743. Min Act: -0.1700
Data Index: 946221 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7431. Min Act: -0.1700
Data Index: 3369413 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7118. Min Act: -0.1700
Data Index: 4170202 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7118. Min Act: -0.1700
Data Index: 263902 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7118. Min Act: -0.1700
Data Index: 4196080 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7118. Min Range: -6.7118
Max Act: 5.7118. Min Act: -0.1700
Data Index: 2048137 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19