Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1584 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1619. Min Range: -4.1619
Max Act: 4.1619. Min Act: -0.1700
Data Index: 6799644 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1619. Min Range: -4.1619
Max Act: 4.0682. Min Act: -0.1700
Data Index: 4167966 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.9744. Min Act: -0.1700
Data Index: 4647241 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.9431. Min Act: -0.1700
Data Index: 4385271 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.9119. Min Act: -0.1700
Data Index: 2805819 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.8493. Min Act: -0.1700
Data Index: 3469847 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.8181. Min Act: -0.1700
Data Index: 6334947 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.8181. Min Act: -0.1700
Data Index: 6350738 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.8181. Min Act: -0.1700
Data Index: 7290692 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.8181. Min Act: -0.1700
Data Index: 7065227 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.8181. Min Act: -0.1700
Data Index: 7003481 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.7868. Min Act: -0.1700
Data Index: 6008538 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.7868. Min Act: -0.1700
Data Index: 4816283 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.7868. Min Act: -0.1700
Data Index: 5934137 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.7555. Min Act: -0.1700
Data Index: 5819970 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.7555. Min Act: -0.1700
Data Index: 2348640 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.7555. Min Act: -0.1700
Data Index: 2212838 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.7555. Min Act: -0.1700
Data Index: 4775599 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.6929. Min Act: -0.1700
Data Index: 3923003 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1619. Min Range: -4.1619
Max Act: 3.7555. Min Act: -0.1700
Data Index: 3400194 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19