Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1691 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.6387. Min Act: -0.1700
Data Index: 1149166 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.5762. Min Act: -0.1700
Data Index: 2117276 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.5450. Min Act: -0.1700
Data Index: 5920534 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.5137. Min Act: -0.1700
Data Index: 5280089 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.5137. Min Act: -0.1700
Data Index: 916404 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.5137. Min Act: -0.1700
Data Index: 3110600 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.5137. Min Act: -0.1700
Data Index: 4834225 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.4825. Min Act: -0.1700
Data Index: 1605441 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.4199. Min Act: -0.1700
Data Index: 45445 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.4199. Min Act: -0.1700
Data Index: 8713391 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3887. Min Act: -0.1700
Data Index: 6465784 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3887. Min Act: -0.1700
Data Index: 4321866 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3574. Min Act: -0.1700
Data Index: 8085962 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3887. Min Act: -0.1700
Data Index: 1958895 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3887. Min Act: -0.1700
Data Index: 4014319 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3262. Min Act: -0.1700
Data Index: 4458857 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3574. Min Act: -0.1700
Data Index: 6830696 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3574. Min Act: -0.1700
Data Index: 4335121 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3574. Min Act: -0.1700
Data Index: 6688205 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6387. Min Range: -4.6387
Max Act: 4.3262. Min Act: -0.1700
Data Index: 3908942 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19