Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2461. Min Range: -3.2461
Max Act: 3.2461. Min Act: -0.1700
Data Index: 1320472 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2461. Min Range: -3.2461
Max Act: 3.1675. Min Act: -0.1700
Data Index: 990360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2461. Min Range: -3.2461
Max Act: 3.1203. Min Act: -0.1700
Data Index: 5314123 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2461. Min Range: -3.2461
Max Act: 3.0888. Min Act: -0.1700
Data Index: 317543 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2461. Min Range: -3.2461
Max Act: 3.0888. Min Act: -0.1700
Data Index: 3529745 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2461. Min Range: -3.2461
Max Act: 3.0414. Min Act: -0.1700
Data Index: 1424929 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2461. Min Range: -3.2461
Max Act: 3.0257. Min Act: -0.1700
Data Index: 2265357 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2461. Min Range: -3.2461
Max Act: 3.0257. Min Act: -0.1700
Data Index: 2938432 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2461. Min Range: -3.2461
Max Act: 3.0099. Min Act: -0.1700
Data Index: 2812258 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9941. Min Act: -0.1700
Data Index: 1985800 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9941. Min Act: -0.1700
Data Index: 8543644 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9941. Min Act: -0.1700
Data Index: 5314132 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9941. Min Act: -0.1700
Data Index: 4206084 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9782. Min Act: -0.1700
Data Index: 7447304 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9782. Min Act: -0.1700
Data Index: 5977784 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9782. Min Act: -0.1700
Data Index: 5739779 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9782. Min Act: -0.1700
Data Index: 105215 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9624. Min Act: -0.1700
Data Index: 4107372 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9466. Min Act: -0.1700
Data Index: 746766 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2461. Min Range: -3.2461
Max Act: 2.9466. Min Act: -0.1700
Data Index: 2251203 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19