Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1965 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4764. Min Act: -0.1700
Data Index: 512560 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4764. Min Act: -0.1700
Data Index: 333569 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4926. Min Act: -0.1700
Data Index: 8415393 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4601. Min Act: -0.1700
Data Index: 6297597 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4601. Min Act: -0.1700
Data Index: 8089417 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4439. Min Act: -0.1700
Data Index: 4308189 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4439. Min Act: -0.1700
Data Index: 229369 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4439. Min Act: -0.1700
Data Index: 229359 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4113. Min Act: -0.1700
Data Index: 3564221 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4601. Min Act: -0.1700
Data Index: 3750113 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4276. Min Act: -0.1700
Data Index: 2258911 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4439. Min Act: -0.1700
Data Index: 2898957 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4439. Min Act: -0.1700
Data Index: 3782734 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4439. Min Act: -0.1700
Data Index: 3065494 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4276. Min Act: -0.1700
Data Index: 5365306 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4276. Min Act: -0.1700
Data Index: 5321044 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.3950. Min Act: -0.1700
Data Index: 5849944 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.4113. Min Act: -0.1700
Data Index: 4435576 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.3787. Min Act: -0.1700
Data Index: 2004395 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4926. Min Range: -2.4926
Max Act: 2.3787. Min Act: -0.1700
Data Index: 157996 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19