Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.9131. Min Act: -0.1700
Data Index: 4402415 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.8193. Min Act: -0.1700
Data Index: 6921974 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.7881. Min Act: -0.1700
Data Index: 7598625 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.7881. Min Act: -0.1700
Data Index: 5332905 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.7256. Min Act: -0.1700
Data Index: 7367320 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.7568. Min Act: -0.1700
Data Index: 3995846 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.6943. Min Act: -0.1700
Data Index: 1952071 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.6631. Min Act: -0.1700
Data Index: 8177172 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.6318. Min Act: -0.1700
Data Index: 5010765 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.6318. Min Act: -0.1700
Data Index: 8055482 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.6318. Min Act: -0.1700
Data Index: 8243681 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.6006. Min Act: -0.1700
Data Index: 6282341 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.5693. Min Act: -0.1700
Data Index: 6902154 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.5068. Min Act: -0.1700
Data Index: 8430924 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.5068. Min Act: -0.1700
Data Index: 2846060 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.5693. Min Act: -0.1700
Data Index: 5865975 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.5068. Min Act: -0.1700
Data Index: 4798276 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.5068. Min Act: -0.1700
Data Index: 3957321 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.5381. Min Act: -0.1700
Data Index: 5730937 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9131. Min Range: -5.9131
Max Act: 5.4756. Min Act: -0.1700
Data Index: 5557083 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19