Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1922 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.3264. Min Act: -0.1700
Data Index: 3231684 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.3420. Min Act: -0.1700
Data Index: 5708102 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.3264. Min Act: -0.1700
Data Index: 7564342 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.3264. Min Act: -0.1700
Data Index: 650500 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.3107. Min Act: -0.1700
Data Index: 2383059 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2950. Min Act: -0.1700
Data Index: 5877560 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2950. Min Act: -0.1700
Data Index: 7937039 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2950. Min Act: -0.1700
Data Index: 2314955 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2950. Min Act: -0.1700
Data Index: 162173 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2636. Min Act: -0.1700
Data Index: 8472224 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2793. Min Act: -0.1700
Data Index: 969764 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2636. Min Act: -0.1700
Data Index: 7110932 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2636. Min Act: -0.1700
Data Index: 6433196 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2636. Min Act: -0.1700
Data Index: 4868125 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2478. Min Act: -0.1700
Data Index: 7275323 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2478. Min Act: -0.1700
Data Index: 6114880 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2478. Min Act: -0.1700
Data Index: 1151181 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2478. Min Act: -0.1700
Data Index: 935593 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2478. Min Act: -0.1700
Data Index: 3441224 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3420. Min Range: -3.3420
Max Act: 3.2164. Min Act: -0.1700
Data Index: 3003402 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19