Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.8627. Min Act: -0.1700
Data Index: 3477072 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.8002. Min Act: -0.1700
Data Index: 7465277 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.7377. Min Act: -0.1700
Data Index: 637515 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.7064. Min Act: -0.1700
Data Index: 4053710 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.6127. Min Act: -0.1700
Data Index: 5663739 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.6127. Min Act: -0.1700
Data Index: 2749458 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.6439. Min Act: -0.1700
Data Index: 7587150 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.5814. Min Act: -0.1700
Data Index: 7270416 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.5814. Min Act: -0.1700
Data Index: 917756 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.5502. Min Act: -0.1700
Data Index: 6315137 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.5502. Min Act: -0.1700
Data Index: 2359973 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.5189. Min Act: -0.1700
Data Index: 8163644 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.5189. Min Act: -0.1700
Data Index: 5108084 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.4877. Min Act: -0.1700
Data Index: 7460015 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.4877. Min Act: -0.1700
Data Index: 3236876 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.4564. Min Act: -0.1700
Data Index: 5734978 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.3939. Min Act: -0.1700
Data Index: 4108129 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.3627. Min Act: -0.1700
Data Index: 8226721 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.3627. Min Act: -0.1700
Data Index: 4142046 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8627. Min Range: -6.8627
Max Act: 6.3627. Min Act: -0.1700
Data Index: 8583959 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19