Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2213 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.3563. Min Act: -0.1700
Data Index: 3152363 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.3250. Min Act: -0.1700
Data Index: 134334 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.2938. Min Act: -0.1700
Data Index: 5490793 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.2313. Min Act: -0.1700
Data Index: 4444184 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.2625. Min Act: -0.1700
Data Index: 2427367 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.2313. Min Act: -0.1700
Data Index: 5225210 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.2313. Min Act: -0.1700
Data Index: 8498996 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.2000. Min Act: -0.1700
Data Index: 4375060 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.1375. Min Act: -0.1700
Data Index: 4215180 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.1688. Min Act: -0.1700
Data Index: 5723974 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.1063. Min Act: -0.1700
Data Index: 7762212 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.1063. Min Act: -0.1700
Data Index: 4845940 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.0750. Min Act: -0.1700
Data Index: 2787416 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.1063. Min Act: -0.1700
Data Index: 2935356 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.0125. Min Act: -0.1700
Data Index: 518190 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.0438. Min Act: -0.1700
Data Index: 5388940 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.0438. Min Act: -0.1700
Data Index: 3773043 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.0438. Min Act: -0.1700
Data Index: 6603116 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.0438. Min Act: -0.1700
Data Index: 2107520 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3563. Min Range: -5.3563
Max Act: 5.0438. Min Act: -0.1700
Data Index: 8439563 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19