Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2953 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.8234. Min Act: -0.1700
Data Index: 1779547 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5422. Min Act: -0.1700
Data Index: 3027694 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5109. Min Act: -0.1700
Data Index: 8173444 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5109. Min Act: -0.1700
Data Index: 747689 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.4484. Min Act: -0.1700
Data Index: 7679004 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.4484. Min Act: -0.1700
Data Index: 8484361 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.3547. Min Act: -0.1700
Data Index: 3456098 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.3547. Min Act: -0.1700
Data Index: 5750136 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.3547. Min Act: -0.1700
Data Index: 7958017 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.3547. Min Act: -0.1700
Data Index: 3156452 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.3547. Min Act: -0.1700
Data Index: 3742662 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.3234. Min Act: -0.1700
Data Index: 8704487 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.3234. Min Act: -0.1700
Data Index: 8021570 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.2922. Min Act: -0.1700
Data Index: 1028318 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.3234. Min Act: -0.1700
Data Index: 4742258 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.3234. Min Act: -0.1700
Data Index: 5510106 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.2922. Min Act: -0.1700
Data Index: 4998381 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.2609. Min Act: -0.1700
Data Index: 5012336 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.2609. Min Act: -0.1700
Data Index: 7747585 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.2609. Min Act: -0.1700
Data Index: 2925798 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19