Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2185 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1546. Min Range: -5.1546
Max Act: 5.1233. Min Act: -0.1700
Data Index: 4037048 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1546. Min Range: -5.1546
Max Act: 5.1546. Min Act: -0.1700
Data Index: 205899 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1546. Min Range: -5.1546
Max Act: 5.0921. Min Act: -0.1700
Data Index: 296841 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1546. Min Range: -5.1546
Max Act: 5.0921. Min Act: -0.1700
Data Index: 7439462 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1546. Min Range: -5.1546
Max Act: 5.0296. Min Act: -0.1700
Data Index: 4927910 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1546. Min Range: -5.1546
Max Act: 5.0296. Min Act: -0.1700
Data Index: 4925531 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.9983. Min Act: -0.1700
Data Index: 8601712 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.9671. Min Act: -0.1700
Data Index: 269554 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.9046. Min Act: -0.1700
Data Index: 4746200 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.9046. Min Act: -0.1700
Data Index: 1614092 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.9046. Min Act: -0.1700
Data Index: 4806622 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.8733. Min Act: -0.1700
Data Index: 3228814 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.9046. Min Act: -0.1700
Data Index: 7028334 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.9358. Min Act: -0.1700
Data Index: 5692533 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.8421. Min Act: -0.1700
Data Index: 4806616 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.8421. Min Act: -0.1700
Data Index: 8380977 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.8421. Min Act: -0.1700
Data Index: 4560170 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.8733. Min Act: -0.1700
Data Index: 7230499 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.7796. Min Act: -0.1700
Data Index: 4666958 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.7796. Min Act: -0.1700
Data Index: 8097070 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19