Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.5139. Min Act: -0.1700
Data Index: 527952 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.4514. Min Act: -0.1700
Data Index: 7949203 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.4514. Min Act: -0.1700
Data Index: 7789277 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.4202. Min Act: -0.1700
Data Index: 347275 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.4202. Min Act: -0.1700
Data Index: 640114 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3577. Min Act: -0.1700
Data Index: 213136 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3889. Min Act: -0.1700
Data Index: 5131920 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3889. Min Act: -0.1700
Data Index: 6130596 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3577. Min Act: -0.1700
Data Index: 4298850 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3577. Min Act: -0.1700
Data Index: 8195124 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3577. Min Act: -0.1700
Data Index: 8265452 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3889. Min Act: -0.1700
Data Index: 5426288 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3577. Min Act: -0.1700
Data Index: 2367896 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3264. Min Act: -0.1700
Data Index: 3533171 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2952. Min Act: -0.1700
Data Index: 4298837 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3264. Min Act: -0.1700
Data Index: 7429191 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.3264. Min Act: -0.1700
Data Index: 8527025 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2952. Min Act: -0.1700
Data Index: 8386691 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2639. Min Act: -0.1700
Data Index: 334899 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5139. Min Range: -5.5139
Max Act: 5.2639. Min Act: -0.1700
Data Index: 527953 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19