Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1628 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.5736. Min Act: -0.1700
Data Index: 2780206 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.4115. Min Act: -0.1700
Data Index: 2806845 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.3952. Min Act: -0.1700
Data Index: 2780204 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.3297. Min Act: -0.1700
Data Index: 528309 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.3133. Min Act: -0.1700
Data Index: 2804520 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.3297. Min Act: -0.1700
Data Index: 1968050 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.3133. Min Act: -0.1700
Data Index: 8465960 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.3297. Min Act: -0.1700
Data Index: 6765500 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2968. Min Act: -0.1700
Data Index: 4869914 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2968. Min Act: -0.1700
Data Index: 2845601 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2804. Min Act: -0.1700
Data Index: 5998348 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2968. Min Act: -0.1700
Data Index: 5311640 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2804. Min Act: -0.1700
Data Index: 4456097 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.3133. Min Act: -0.1700
Data Index: 6815845 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2968. Min Act: -0.1700
Data Index: 958756 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2639. Min Act: -0.1700
Data Index: 8235354 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2474. Min Act: -0.1700
Data Index: 6676547 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2968. Min Act: -0.1700
Data Index: 1916605 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2639. Min Act: -0.1700
Data Index: 3264015 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5736. Min Range: -2.5736
Max Act: 2.2474. Min Act: -0.1700
Data Index: 1104350 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19