Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 882 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6722. Min Range: -6.6722
Max Act: 6.6722. Min Act: -0.1700
Data Index: 2634892 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.9535. Min Act: -0.1700
Data Index: 537073 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.9847. Min Act: -0.1700
Data Index: 623067 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.8597. Min Act: -0.1700
Data Index: 7322656 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.7035. Min Act: -0.1700
Data Index: 6892764 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.7035. Min Act: -0.1700
Data Index: 7307257 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.7035. Min Act: -0.1700
Data Index: 3398363 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.6410. Min Act: -0.1700
Data Index: 8371359 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.6722. Min Act: -0.1700
Data Index: 5842620 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.6410. Min Act: -0.1700
Data Index: 5719591 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.5785. Min Act: -0.1700
Data Index: 5276426 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.6097. Min Act: -0.1700
Data Index: 4107556 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.5472. Min Act: -0.1700
Data Index: 1832974 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.5472. Min Act: -0.1700
Data Index: 1848979 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.5472. Min Act: -0.1700
Data Index: 4933172 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.5472. Min Act: -0.1700
Data Index: 1374963 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.5472. Min Act: -0.1700
Data Index: 2619906 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.4847. Min Act: -0.1700
Data Index: 5612906 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.5472. Min Act: -0.1700
Data Index: 537074 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6722. Min Range: -6.6722
Max Act: 5.5160. Min Act: -0.1700
Data Index: 5891684 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19