Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1771 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1081. Min Range: -3.1081
Max Act: 3.1081. Min Act: -0.1700
Data Index: 1710044 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1081. Min Range: -3.1081
Max Act: 3.0608. Min Act: -0.1700
Data Index: 7333712 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1081. Min Range: -3.1081
Max Act: 3.0134. Min Act: -0.1700
Data Index: 3195760 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9818. Min Act: -0.1700
Data Index: 6438940 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9818. Min Act: -0.1700
Data Index: 5126957 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9660. Min Act: -0.1700
Data Index: 3060260 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9660. Min Act: -0.1700
Data Index: 8137453 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9185. Min Act: -0.1700
Data Index: 807678 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9502. Min Act: -0.1700
Data Index: 8029398 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9344. Min Act: -0.1700
Data Index: 4383253 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9344. Min Act: -0.1700
Data Index: 6511257 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9344. Min Act: -0.1700
Data Index: 8766791 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9185. Min Act: -0.1700
Data Index: 4745480 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9185. Min Act: -0.1700
Data Index: 8722458 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9027. Min Act: -0.1700
Data Index: 1053078 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9185. Min Act: -0.1700
Data Index: 5567460 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9027. Min Act: -0.1700
Data Index: 2961132 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9027. Min Act: -0.1700
Data Index: 1906973 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9027. Min Act: -0.1700
Data Index: 6237880 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1081. Min Range: -3.1081
Max Act: 2.9027. Min Act: -0.1700
Data Index: 8682141 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19