Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0463. Min Range: -5.0463
Max Act: 5.0463. Min Act: -0.1700
Data Index: 6072993 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0463. Min Range: -5.0463
Max Act: 5.0463. Min Act: -0.1700
Data Index: 2844019 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.9838. Min Act: -0.1700
Data Index: 3177976 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.9213. Min Act: -0.1700
Data Index: 7421961 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.8276. Min Act: -0.1700
Data Index: 754175 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.8276. Min Act: -0.1700
Data Index: 8800587 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7651. Min Act: -0.1700
Data Index: 3380464 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7963. Min Act: -0.1700
Data Index: 2091901 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7338. Min Act: -0.1700
Data Index: 5476784 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7651. Min Act: -0.1700
Data Index: 3480622 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7651. Min Act: -0.1700
Data Index: 1214387 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7651. Min Act: -0.1700
Data Index: 1143715 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7338. Min Act: -0.1700
Data Index: 2178776 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7338. Min Act: -0.1700
Data Index: 7399715 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7338. Min Act: -0.1700
Data Index: 2265053 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7338. Min Act: -0.1700
Data Index: 8709308 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7338. Min Act: -0.1700
Data Index: 1178199 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7026. Min Act: -0.1700
Data Index: 8179079 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7026. Min Act: -0.1700
Data Index: 2091895 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0463. Min Range: -5.0463
Max Act: 4.7026. Min Act: -0.1700
Data Index: 2957906 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19