Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1367 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0536. Min Range: -6.0536
Max Act: 6.0536. Min Act: -0.1700
Data Index: 2405545 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.9598. Min Act: -0.1700
Data Index: 6769219 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.8348. Min Act: -0.1700
Data Index: 3661661 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7411. Min Act: -0.1700
Data Index: 6516865 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7723. Min Act: -0.1700
Data Index: 7990327 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7411. Min Act: -0.1700
Data Index: 4245109 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7098. Min Act: -0.1700
Data Index: 7397665 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7098. Min Act: -0.1700
Data Index: 2737031 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.6473. Min Act: -0.1700
Data Index: 733881 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.6473. Min Act: -0.1700
Data Index: 8286852 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5536. Min Act: -0.1700
Data Index: 4732335 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5536. Min Act: -0.1700
Data Index: 3677918 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5223. Min Act: -0.1700
Data Index: 5567797 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5223. Min Act: -0.1700
Data Index: 274819 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5536. Min Act: -0.1700
Data Index: 3681327 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5536. Min Act: -0.1700
Data Index: 1367629 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.4911. Min Act: -0.1700
Data Index: 5286726 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.4598. Min Act: -0.1700
Data Index: 8214134 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.3973. Min Act: -0.1700
Data Index: 3839362 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.4911. Min Act: -0.1700
Data Index: 282629 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19