Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 501 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1134. Min Range: -5.1134
Max Act: 5.1134. Min Act: -0.1700
Data Index: 3299447 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1134. Min Range: -5.1134
Max Act: 5.0821. Min Act: -0.1700
Data Index: 6550582 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1134. Min Range: -5.1134
Max Act: 5.0509. Min Act: -0.1700
Data Index: 3986763 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.9884. Min Act: -0.1700
Data Index: 4736077 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.9571. Min Act: -0.1700
Data Index: 7615687 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.9571. Min Act: -0.1700
Data Index: 5644 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.9259. Min Act: -0.1700
Data Index: 6122014 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8946. Min Act: -0.1700
Data Index: 268722 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.9259. Min Act: -0.1700
Data Index: 1413282 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8634. Min Act: -0.1700
Data Index: 5414391 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8946. Min Act: -0.1700
Data Index: 393775 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8634. Min Act: -0.1700
Data Index: 4649612 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 3222049 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8321. Min Act: -0.1700
Data Index: 7669162 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 4984636 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 6122016 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 3551224 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 2205981 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 7184148 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1134. Min Range: -5.1134
Max Act: 4.8009. Min Act: -0.1700
Data Index: 7225220 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19