Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1784 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.8609. Min Act: -0.1700
Data Index: 5388429 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.8296. Min Act: -0.1700
Data Index: 2900593 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6734. Min Act: -0.1700
Data Index: 2192525 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6734. Min Act: -0.1700
Data Index: 4136148 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6421. Min Act: -0.1700
Data Index: 3292621 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6421. Min Act: -0.1700
Data Index: 5427225 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6421. Min Act: -0.1700
Data Index: 7871608 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6421. Min Act: -0.1700
Data Index: 1902463 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6421. Min Act: -0.1700
Data Index: 8384925 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.5796. Min Act: -0.1700
Data Index: 5299392 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6108. Min Act: -0.1700
Data Index: 1791306 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6108. Min Act: -0.1700
Data Index: 5198846 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.5796. Min Act: -0.1700
Data Index: 5700980 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6108. Min Act: -0.1700
Data Index: 8550780 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.5796. Min Act: -0.1700
Data Index: 4856706 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.5796. Min Act: -0.1700
Data Index: 2012519 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.5796. Min Act: -0.1700
Data Index: 6986952 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.5483. Min Act: -0.1700
Data Index: 7408788 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.5796. Min Act: -0.1700
Data Index: 8718620 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8609. Min Range: -4.8609
Max Act: 4.6108. Min Act: -0.1700
Data Index: 4910017 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19