Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4921 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.7526. Min Act: -0.1700
Data Index: 8811615 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.7526. Min Act: -0.1700
Data Index: 2745112 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.6901. Min Act: -0.1700
Data Index: 7447766 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.7214. Min Act: -0.1700
Data Index: 3434089 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.7214. Min Act: -0.1700
Data Index: 4504543 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.6901. Min Act: -0.1700
Data Index: 7373277 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.6901. Min Act: -0.1700
Data Index: 2966098 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.6901. Min Act: -0.1700
Data Index: 2234584 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.6901. Min Act: -0.1700
Data Index: 7382312 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.6588. Min Act: -0.1700
Data Index: 3445420 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.6588. Min Act: -0.1700
Data Index: 2810807 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.6588. Min Act: -0.1700
Data Index: 7624224 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.6275. Min Act: -0.1700
Data Index: 651639 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.5962. Min Act: -0.1700
Data Index: 5021368 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.5962. Min Act: -0.1700
Data Index: 7882176 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.5962. Min Act: -0.1700
Data Index: 4517525 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.5649. Min Act: -0.1700
Data Index: 2724704 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.5962. Min Act: -0.1700
Data Index: 4811501 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.5962. Min Act: -0.1700
Data Index: 8340104 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7526. Min Range: -3.7526
Max Act: 3.5962. Min Act: -0.1700
Data Index: 4231026 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19