Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1491. Min Range: -5.1491
Max Act: 5.1491. Min Act: -0.1700
Data Index: 6743115 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1491. Min Range: -5.1491
Max Act: 5.1178. Min Act: -0.1700
Data Index: 4998642 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1491. Min Range: -5.1491
Max Act: 5.1178. Min Act: -0.1700
Data Index: 8479414 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1491. Min Range: -5.1491
Max Act: 5.0241. Min Act: -0.1700
Data Index: 6763599 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1491. Min Range: -5.1491
Max Act: 5.0241. Min Act: -0.1700
Data Index: 228816 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.9616. Min Act: -0.1700
Data Index: 663751 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.9616. Min Act: -0.1700
Data Index: 6689241 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.9303. Min Act: -0.1700
Data Index: 5717307 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.8991. Min Act: -0.1700
Data Index: 2560551 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.8991. Min Act: -0.1700
Data Index: 6370380 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.9303. Min Act: -0.1700
Data Index: 4198670 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.8678. Min Act: -0.1700
Data Index: 3256042 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.8678. Min Act: -0.1700
Data Index: 6040164 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.8366. Min Act: -0.1700
Data Index: 7374142 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.8366. Min Act: -0.1700
Data Index: 2364049 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.8366. Min Act: -0.1700
Data Index: 6271440 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.8053. Min Act: -0.1700
Data Index: 6792056 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.7741. Min Act: -0.1700
Data Index: 6639506 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.7741. Min Act: -0.1700
Data Index: 1199278 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1491. Min Range: -5.1491
Max Act: 4.7741. Min Act: -0.1700
Data Index: 3439518 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19