Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1212 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0776. Min Range: -6.0776
Max Act: 6.0776. Min Act: -0.1700
Data Index: 204890 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.8901. Min Act: -0.1700
Data Index: 8144125 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.7651. Min Act: -0.1700
Data Index: 7601558 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.6714. Min Act: -0.1700
Data Index: 4285902 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.6089. Min Act: -0.1700
Data Index: 7061012 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.5776. Min Act: -0.1700
Data Index: 7940035 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.5464. Min Act: -0.1700
Data Index: 4097145 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.5151. Min Act: -0.1700
Data Index: 2424527 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.5151. Min Act: -0.1700
Data Index: 2490579 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.5151. Min Act: -0.1700
Data Index: 4603277 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.4839. Min Act: -0.1700
Data Index: 186272 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.4214. Min Act: -0.1700
Data Index: 8758867 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.4526. Min Act: -0.1700
Data Index: 8115274 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.4839. Min Act: -0.1700
Data Index: 3682435 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.4214. Min Act: -0.1700
Data Index: 1277414 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.4526. Min Act: -0.1700
Data Index: 94980 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.4214. Min Act: -0.1700
Data Index: 6817180 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.4214. Min Act: -0.1700
Data Index: 6085053 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.3901. Min Act: -0.1700
Data Index: 7139629 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0776. Min Range: -6.0776
Max Act: 5.3901. Min Act: -0.1700
Data Index: 6626953 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19