Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1251 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.9702. Min Act: -0.1700
Data Index: 7820315 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.9077. Min Act: -0.1700
Data Index: 8664304 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.9077. Min Act: -0.1700
Data Index: 2487541 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.8139. Min Act: -0.1700
Data Index: 3328650 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.8452. Min Act: -0.1700
Data Index: 8134056 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.8452. Min Act: -0.1700
Data Index: 6739272 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7827. Min Act: -0.1700
Data Index: 2511297 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7202. Min Act: -0.1700
Data Index: 769166 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7514. Min Act: -0.1700
Data Index: 3249417 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7514. Min Act: -0.1700
Data Index: 960579 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7514. Min Act: -0.1700
Data Index: 8200895 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7514. Min Act: -0.1700
Data Index: 3347407 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7514. Min Act: -0.1700
Data Index: 4245024 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7514. Min Act: -0.1700
Data Index: 2674987 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7514. Min Act: -0.1700
Data Index: 3591534 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7202. Min Act: -0.1700
Data Index: 7407297 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7202. Min Act: -0.1700
Data Index: 5532909 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7202. Min Act: -0.1700
Data Index: 5599367 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7202. Min Act: -0.1700
Data Index: 4469107 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9702. Min Range: -4.9702
Max Act: 4.7202. Min Act: -0.1700
Data Index: 919149 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19