Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2203 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4257. Min Range: -5.4257
Max Act: 5.4257. Min Act: -0.1700
Data Index: 4519780 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4257. Min Range: -5.4257
Max Act: 5.0507. Min Act: -0.1700
Data Index: 321209 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4257. Min Range: -5.4257
Max Act: 5.0195. Min Act: -0.1700
Data Index: 2942458 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.9570. Min Act: -0.1700
Data Index: 6151086 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.9257. Min Act: -0.1700
Data Index: 1227404 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.8632. Min Act: -0.1700
Data Index: 1944933 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.8320. Min Act: -0.1700
Data Index: 3479356 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.8632. Min Act: -0.1700
Data Index: 5637839 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.8320. Min Act: -0.1700
Data Index: 6150440 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.8632. Min Act: -0.1700
Data Index: 3933091 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.8320. Min Act: -0.1700
Data Index: 7899552 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.8007. Min Act: -0.1700
Data Index: 7008950 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.8007. Min Act: -0.1700
Data Index: 3021396 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.7382. Min Act: -0.1700
Data Index: 2290650 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.7382. Min Act: -0.1700
Data Index: 1815383 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.7382. Min Act: -0.1700
Data Index: 4614675 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.7382. Min Act: -0.1700
Data Index: 6969796 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.7382. Min Act: -0.1700
Data Index: 727638 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.7382. Min Act: -0.1700
Data Index: 3843001 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4257. Min Range: -5.4257
Max Act: 4.7070. Min Act: -0.1700
Data Index: 4387439 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19