Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.5383. Min Act: -0.1700
Data Index: 5258284 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.5696. Min Act: -0.1700
Data Index: 4402315 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.5383. Min Act: -0.1700
Data Index: 2246937 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.5227. Min Act: -0.1700
Data Index: 783036 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.5070. Min Act: -0.1700
Data Index: 2875324 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.4913. Min Act: -0.1700
Data Index: 1664551 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.4600. Min Act: -0.1700
Data Index: 4807290 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.4443. Min Act: -0.1700
Data Index: 1316706 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.4600. Min Act: -0.1700
Data Index: 8007275 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.4130. Min Act: -0.1700
Data Index: 5559304 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.4130. Min Act: -0.1700
Data Index: 1066102 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.4130. Min Act: -0.1700
Data Index: 8375996 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.4287. Min Act: -0.1700
Data Index: 6841677 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.3973. Min Act: -0.1700
Data Index: 6135784 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.4130. Min Act: -0.1700
Data Index: 2868477 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.3816. Min Act: -0.1700
Data Index: 5167011 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.3816. Min Act: -0.1700
Data Index: 445921 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.3973. Min Act: -0.1700
Data Index: 4682701 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.3660. Min Act: -0.1700
Data Index: 687996 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5696. Min Range: -3.5696
Max Act: 3.3660. Min Act: -0.1700
Data Index: 7875958 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19