Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1170 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0532. Min Range: -3.0532
Max Act: 3.0532. Min Act: -0.1700
Data Index: 7419811 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0532. Min Range: -3.0532
Max Act: 3.0374. Min Act: -0.1700
Data Index: 2683026 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0532. Min Range: -3.0532
Max Act: 3.0058. Min Act: -0.1700
Data Index: 6320854 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0532. Min Range: -3.0532
Max Act: 3.0058. Min Act: -0.1700
Data Index: 4563650 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9900. Min Act: -0.1700
Data Index: 4699368 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9584. Min Act: -0.1700
Data Index: 4452309 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9584. Min Act: -0.1700
Data Index: 3632958 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9425. Min Act: -0.1700
Data Index: 2764826 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9425. Min Act: -0.1700
Data Index: 4790800 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9425. Min Act: -0.1700
Data Index: 3116971 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9267. Min Act: -0.1700
Data Index: 4407994 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9108. Min Act: -0.1700
Data Index: 4920184 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9108. Min Act: -0.1700
Data Index: 2323290 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8950. Min Act: -0.1700
Data Index: 3966466 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8950. Min Act: -0.1700
Data Index: 6448430 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8950. Min Act: -0.1700
Data Index: 721400 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8950. Min Act: -0.1700
Data Index: 1527095 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.8950. Min Act: -0.1700
Data Index: 1616012 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9108. Min Act: -0.1700
Data Index: 6108726 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0532. Min Range: -3.0532
Max Act: 2.9108. Min Act: -0.1700
Data Index: 1391852 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19