Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4915 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8037. Min Range: -6.8037
Max Act: 6.8037. Min Act: -0.1700
Data Index: 4261837 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8037. Min Range: -6.8037
Max Act: 6.5225. Min Act: -0.1700
Data Index: 3831550 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8037. Min Range: -6.8037
Max Act: 6.2725. Min Act: -0.1700
Data Index: 939641 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8037. Min Range: -6.8037
Max Act: 6.1475. Min Act: -0.1700
Data Index: 4513679 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8037. Min Range: -6.8037
Max Act: 6.0225. Min Act: -0.1700
Data Index: 7335098 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8037. Min Range: -6.8037
Max Act: 6.0537. Min Act: -0.1700
Data Index: 3984289 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.9912. Min Act: -0.1700
Data Index: 4152805 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8037. Min Range: -6.8037
Max Act: 6.0225. Min Act: -0.1700
Data Index: 1524408 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.9600. Min Act: -0.1700
Data Index: 3434945 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.9912. Min Act: -0.1700
Data Index: 4498208 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.9912. Min Act: -0.1700
Data Index: 5419404 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.9600. Min Act: -0.1700
Data Index: 4803741 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.9600. Min Act: -0.1700
Data Index: 2835963 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.8975. Min Act: -0.1700
Data Index: 5287434 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.9287. Min Act: -0.1700
Data Index: 2255020 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.9287. Min Act: -0.1700
Data Index: 6621686 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.8975. Min Act: -0.1700
Data Index: 8638338 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.8350. Min Act: -0.1700
Data Index: 7838586 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.8662. Min Act: -0.1700
Data Index: 5561857 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8037. Min Range: -6.8037
Max Act: 5.8350. Min Act: -0.1700
Data Index: 4859875 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19