Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4931. Min Range: -9.4931
Max Act: 9.4306. Min Act: -0.1700
Data Index: 1322195 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4931. Min Range: -9.4931
Max Act: 9.4306. Min Act: -0.1700
Data Index: 371368 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4931. Min Range: -9.4931
Max Act: 9.2431. Min Act: -0.1700
Data Index: 6878378 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4931. Min Range: -9.4931
Max Act: 9.4931. Min Act: -0.1700
Data Index: 6878376 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4931. Min Range: -9.4931
Max Act: 9.0556. Min Act: -0.1700
Data Index: 6878379 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4931. Min Range: -9.4931
Max Act: 9.1806. Min Act: -0.1700
Data Index: 4917076 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4931. Min Range: -9.4931
Max Act: 9.1181. Min Act: -0.1700
Data Index: 6878377 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.9306. Min Act: -0.1700
Data Index: 371369 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.9931. Min Act: -0.1700
Data Index: 5484580 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.9931. Min Act: -0.1700
Data Index: 3046116 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.9306. Min Act: -0.1700
Data Index: 371370 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.8681. Min Act: -0.1700
Data Index: 6066631 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.8056. Min Act: -0.1700
Data Index: 5833569 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.7431. Min Act: -0.1700
Data Index: 5100869 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.8056. Min Act: -0.1700
Data Index: 4640051 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.8056. Min Act: -0.1700
Data Index: 8382844 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.7431. Min Act: -0.1700
Data Index: 2627613 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.8056. Min Act: -0.1700
Data Index: 1240042 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.7431. Min Act: -0.1700
Data Index: 492301 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4931. Min Range: -9.4931
Max Act: 8.7431. Min Act: -0.1698
Data Index: 836916 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19