Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 87 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.6808. Min Act: -0.1700
Data Index: 8599011 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.6183. Min Act: -0.1700
Data Index: 6715905 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.6183. Min Act: -0.1700
Data Index: 1940276 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.4933. Min Act: -0.1700
Data Index: 4859510 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.4933. Min Act: -0.1700
Data Index: 8327872 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.4933. Min Act: -0.1700
Data Index: 6701635 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.4933. Min Act: -0.1700
Data Index: 6634056 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.3683. Min Act: -0.1700
Data Index: 7462874 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.3683. Min Act: -0.1700
Data Index: 4472430 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.3371. Min Act: -0.1700
Data Index: 8598621 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.2746. Min Act: -0.1700
Data Index: 8528527 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.2746. Min Act: -0.1700
Data Index: 3551789 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.3058. Min Act: -0.1700
Data Index: 840022 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.2746. Min Act: -0.1700
Data Index: 340051 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.2433. Min Act: -0.1700
Data Index: 5595133 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.2121. Min Act: -0.1700
Data Index: 1909071 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.1808. Min Act: -0.1700
Data Index: 4004445 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.2121. Min Act: -0.1700
Data Index: 4182882 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.2433. Min Act: -0.1700
Data Index: 7847371 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6808. Min Range: -6.6808
Max Act: 6.1808. Min Act: -0.1700
Data Index: 7156444 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19