Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4281 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.4731. Min Act: -0.1700
Data Index: 3336846 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.1919. Min Act: -0.1700
Data Index: 3088779 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.2231. Min Act: -0.1700
Data Index: 2106150 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.1919. Min Act: -0.1700
Data Index: 2272128 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.1294. Min Act: -0.1700
Data Index: 6250286 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.0981. Min Act: -0.1700
Data Index: 8028424 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.0981. Min Act: -0.1700
Data Index: 2069343 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.0669. Min Act: -0.1700
Data Index: 5946453 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.0669. Min Act: -0.1700
Data Index: 6377157 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.0356. Min Act: -0.1700
Data Index: 2508835 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.0356. Min Act: -0.1700
Data Index: 3749611 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.0356. Min Act: -0.1700
Data Index: 3307188 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.0044. Min Act: -0.1700
Data Index: 3432639 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4731. Min Range: -7.4731
Max Act: 7.0044. Min Act: -0.1700
Data Index: 5389520 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4731. Min Range: -7.4731
Max Act: 6.9731. Min Act: -0.1700
Data Index: 7447367 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4731. Min Range: -7.4731
Max Act: 6.9731. Min Act: -0.1700
Data Index: 7791597 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4731. Min Range: -7.4731
Max Act: 6.9419. Min Act: -0.1700
Data Index: 4305723 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4731. Min Range: -7.4731
Max Act: 6.9419. Min Act: -0.1700
Data Index: 3779587 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4731. Min Range: -7.4731
Max Act: 6.9106. Min Act: -0.1700
Data Index: 7686329 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4731. Min Range: -7.4731
Max Act: 6.9106. Min Act: -0.1700
Data Index: 4437367 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19