Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2112 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.7540. Min Act: -0.1700
Data Index: 1953168 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.6132. Min Act: -0.1700
Data Index: 3221412 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.5975. Min Act: -0.1700
Data Index: 675895 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.5349. Min Act: -0.1700
Data Index: 8070680 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.5192. Min Act: -0.1700
Data Index: 900054 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.5349. Min Act: -0.1700
Data Index: 784089 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.5036. Min Act: -0.1700
Data Index: 6609808 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.5036. Min Act: -0.1700
Data Index: 1398556 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4879. Min Act: -0.1700
Data Index: 8730019 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.5036. Min Act: -0.1700
Data Index: 7668236 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4722. Min Act: -0.1700
Data Index: 2625427 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4879. Min Act: -0.1700
Data Index: 7031860 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4722. Min Act: -0.1700
Data Index: 2193283 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4409. Min Act: -0.1700
Data Index: 8089037 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4566. Min Act: -0.1700
Data Index: 5849506 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4409. Min Act: -0.1700
Data Index: 201446 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4252. Min Act: -0.1700
Data Index: 7330568 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4096. Min Act: -0.1700
Data Index: 5425264 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4252. Min Act: -0.1700
Data Index: 5662271 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7540. Min Range: -3.7540
Max Act: 3.4252. Min Act: -0.1700
Data Index: 4410057 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19