Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1916 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.9146. Min Act: -0.1700
Data Index: 4751485 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.7896. Min Act: -0.1700
Data Index: 2729690 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.6021. Min Act: -0.1700
Data Index: 4442120 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.5396. Min Act: -0.1700
Data Index: 8161403 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.5396. Min Act: -0.1700
Data Index: 69015 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.5083. Min Act: -0.1700
Data Index: 814830 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.5083. Min Act: -0.1700
Data Index: 5965366 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.4771. Min Act: -0.1700
Data Index: 2801317 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.4771. Min Act: -0.1700
Data Index: 8123590 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.4458. Min Act: -0.1700
Data Index: 1100191 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.4458. Min Act: -0.1700
Data Index: 7270564 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.4146. Min Act: -0.1700
Data Index: 7887205 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.4146. Min Act: -0.1700
Data Index: 4242878 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.4146. Min Act: -0.1700
Data Index: 4245185 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.3521. Min Act: -0.1700
Data Index: 6891631 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.3833. Min Act: -0.1700
Data Index: 3935065 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.3521. Min Act: -0.1700
Data Index: 7992653 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.3521. Min Act: -0.1700
Data Index: 4902991 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.3208. Min Act: -0.1700
Data Index: 628423 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9146. Min Range: -5.9146
Max Act: 5.3208. Min Act: -0.1700
Data Index: 4752014 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19