Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1403 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1460. Min Range: -4.1460
Max Act: 4.1147. Min Act: -0.1700
Data Index: 2643238 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1460. Min Range: -4.1460
Max Act: 4.1460. Min Act: -0.1700
Data Index: 2287943 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1460. Min Range: -4.1460
Max Act: 4.0522. Min Act: -0.1700
Data Index: 812694 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1460. Min Range: -4.1460
Max Act: 4.1147. Min Act: -0.1700
Data Index: 4322742 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1460. Min Range: -4.1460
Max Act: 4.0522. Min Act: -0.1700
Data Index: 3094984 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9897. Min Act: -0.1700
Data Index: 3985692 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9897. Min Act: -0.1700
Data Index: 1477705 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1460. Min Range: -4.1460
Max Act: 4.0210. Min Act: -0.1700
Data Index: 3467059 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9585. Min Act: -0.1700
Data Index: 2938786 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9897. Min Act: -0.1700
Data Index: 6989711 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9272. Min Act: -0.1700
Data Index: 5725873 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9897. Min Act: -0.1700
Data Index: 2224710 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9897. Min Act: -0.1700
Data Index: 5643675 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.8959. Min Act: -0.1700
Data Index: 1633793 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9897. Min Act: -0.1700
Data Index: 7955524 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9897. Min Act: -0.1700
Data Index: 7353846 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9272. Min Act: -0.1700
Data Index: 116387 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9585. Min Act: -0.1700
Data Index: 3782540 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9272. Min Act: -0.1700
Data Index: 812056 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1460. Min Range: -4.1460
Max Act: 3.9897. Min Act: -0.1700
Data Index: 5619225 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19