Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1237 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.5341. Min Act: -0.1700
Data Index: 332521 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.5028. Min Act: -0.1700
Data Index: 5065321 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.4403. Min Act: -0.1700
Data Index: 8337755 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.4403. Min Act: -0.1700
Data Index: 4150211 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.3466. Min Act: -0.1700
Data Index: 4889039 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.3153. Min Act: -0.1700
Data Index: 7444314 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2216. Min Act: -0.1700
Data Index: 757823 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2528. Min Act: -0.1700
Data Index: 5873655 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.1903. Min Act: -0.1700
Data Index: 2567189 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.1591. Min Act: -0.1700
Data Index: 2651051 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.1591. Min Act: -0.1700
Data Index: 8737746 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.1591. Min Act: -0.1700
Data Index: 1017071 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.1591. Min Act: -0.1700
Data Index: 1534519 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.0653. Min Act: -0.1700
Data Index: 5745071 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.0653. Min Act: -0.1700
Data Index: 1762597 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.0341. Min Act: -0.1700
Data Index: 7155654 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.0341. Min Act: -0.1700
Data Index: 7877650 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.0341. Min Act: -0.1700
Data Index: 2480600 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.0653. Min Act: -0.1700
Data Index: 6249308 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.0028. Min Act: -0.1700
Data Index: 5832952 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19