Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3287 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0616. Min Range: -3.0616
Max Act: 3.0616. Min Act: -0.1700
Data Index: 3378723 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0616. Min Range: -3.0616
Max Act: 3.0301. Min Act: -0.1700
Data Index: 3625864 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0616. Min Range: -3.0616
Max Act: 3.0143. Min Act: -0.1700
Data Index: 2849671 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.9510. Min Act: -0.1700
Data Index: 1922788 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.9510. Min Act: -0.1700
Data Index: 624628 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.9510. Min Act: -0.1700
Data Index: 5176467 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.9194. Min Act: -0.1700
Data Index: 3585460 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.9194. Min Act: -0.1700
Data Index: 3912138 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.9035. Min Act: -0.1700
Data Index: 3594701 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.8876. Min Act: -0.1700
Data Index: 1412844 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.9035. Min Act: -0.1700
Data Index: 3483895 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.9035. Min Act: -0.1700
Data Index: 1803310 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.8718. Min Act: -0.1700
Data Index: 3478305 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.8559. Min Act: -0.1700
Data Index: 875291 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.8559. Min Act: -0.1700
Data Index: 2193493 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.8400. Min Act: -0.1700
Data Index: 4012439 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.8559. Min Act: -0.1700
Data Index: 2695261 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.8400. Min Act: -0.1700
Data Index: 665177 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.8400. Min Act: -0.1700
Data Index: 379524 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0616. Min Range: -3.0616
Max Act: 2.8400. Min Act: -0.1700
Data Index: 3039953 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19