Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1508 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1258. Min Range: -6.1258
Max Act: 6.1258. Min Act: -0.1700
Data Index: 1513825 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.9071. Min Act: -0.1700
Data Index: 3398279 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.7821. Min Act: -0.1700
Data Index: 5569259 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.7508. Min Act: -0.1700
Data Index: 1145858 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.7821. Min Act: -0.1700
Data Index: 988500 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.6883. Min Act: -0.1700
Data Index: 1380810 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.6883. Min Act: -0.1700
Data Index: 471701 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.6571. Min Act: -0.1700
Data Index: 6916618 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.6258. Min Act: -0.1700
Data Index: 5050826 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.6571. Min Act: -0.1700
Data Index: 6690206 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5946. Min Act: -0.1700
Data Index: 5073903 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5946. Min Act: -0.1700
Data Index: 6637446 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5946. Min Act: -0.1700
Data Index: 1200367 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5946. Min Act: -0.1700
Data Index: 5785192 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5946. Min Act: -0.1700
Data Index: 2422487 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5633. Min Act: -0.1700
Data Index: 932518 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5321. Min Act: -0.1700
Data Index: 5882772 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5633. Min Act: -0.1700
Data Index: 471698 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5633. Min Act: -0.1700
Data Index: 4155008 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1258. Min Range: -6.1258
Max Act: 5.5633. Min Act: -0.1700
Data Index: 2334650 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19