Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1693. Min Range: -4.1693
Max Act: 4.1693. Min Act: -0.1700
Data Index: 8645276 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1693. Min Range: -4.1693
Max Act: 4.0443. Min Act: -0.1700
Data Index: 5080486 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1693. Min Range: -4.1693
Max Act: 4.0130. Min Act: -0.1700
Data Index: 2274940 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1693. Min Range: -4.1693
Max Act: 4.0130. Min Act: -0.1700
Data Index: 98155 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.9505. Min Act: -0.1700
Data Index: 1868701 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.9505. Min Act: -0.1700
Data Index: 4753704 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.9192. Min Act: -0.1700
Data Index: 3579179 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8880. Min Act: -0.1700
Data Index: 4943101 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8880. Min Act: -0.1700
Data Index: 5538468 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8880. Min Act: -0.1700
Data Index: 3062100 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8567. Min Act: -0.1700
Data Index: 7615841 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8567. Min Act: -0.1700
Data Index: 7793170 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8567. Min Act: -0.1700
Data Index: 468997 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8567. Min Act: -0.1700
Data Index: 6776387 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8254. Min Act: -0.1700
Data Index: 6955095 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8254. Min Act: -0.1700
Data Index: 4157998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8254. Min Act: -0.1700
Data Index: 718895 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8254. Min Act: -0.1700
Data Index: 6754334 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8567. Min Act: -0.1700
Data Index: 456253 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1693. Min Range: -4.1693
Max Act: 3.8254. Min Act: -0.1700
Data Index: 6470597 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19