Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9876. Min Act: -0.1700
Data Index: 4340420 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9718. Min Act: -0.1700
Data Index: 1084973 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9560. Min Act: -0.1700
Data Index: 2387053 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9718. Min Act: -0.1700
Data Index: 2234831 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9560. Min Act: -0.1700
Data Index: 2750513 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9560. Min Act: -0.1700
Data Index: 3556276 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9560. Min Act: -0.1700
Data Index: 1455086 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9560. Min Act: -0.1700
Data Index: 1707175 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9243. Min Act: -0.1700
Data Index: 1209656 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9243. Min Act: -0.1700
Data Index: 5402451 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9085. Min Act: -0.1700
Data Index: 8505180 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9243. Min Act: -0.1700
Data Index: 2635591 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9243. Min Act: -0.1700
Data Index: 4401455 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9085. Min Act: -0.1700
Data Index: 5678719 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9402. Min Act: -0.1700
Data Index: 1575646 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9243. Min Act: -0.1700
Data Index: 7960757 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9085. Min Act: -0.1700
Data Index: 13153 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9085. Min Act: -0.1700
Data Index: 769527 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9085. Min Act: -0.1700
Data Index: 1420722 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9876. Min Range: -2.9876
Max Act: 2.9085. Min Act: -0.1700
Data Index: 4740908 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19