Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5357 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3605. Min Range: -6.3605
Max Act: 6.3605. Min Act: -0.1700
Data Index: 6405106 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3605. Min Range: -6.3605
Max Act: 6.2355. Min Act: -0.1700
Data Index: 6704723 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3605. Min Range: -6.3605
Max Act: 6.0167. Min Act: -0.1700
Data Index: 581805 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9855. Min Act: -0.1700
Data Index: 5200915 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9855. Min Act: -0.1700
Data Index: 1670467 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3605. Min Range: -6.3605
Max Act: 6.0167. Min Act: -0.1700
Data Index: 5111756 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9542. Min Act: -0.1700
Data Index: 4526245 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9542. Min Act: -0.1700
Data Index: 1055901 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9230. Min Act: -0.1700
Data Index: 4903702 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9230. Min Act: -0.1700
Data Index: 6735647 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9230. Min Act: -0.1700
Data Index: 1225334 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9230. Min Act: -0.1700
Data Index: 8787027 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.8917. Min Act: -0.1700
Data Index: 109423 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9230. Min Act: -0.1700
Data Index: 3571369 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.9230. Min Act: -0.1700
Data Index: 5775775 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.8292. Min Act: -0.1700
Data Index: 352330 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.8605. Min Act: -0.1700
Data Index: 8017168 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.8917. Min Act: -0.1700
Data Index: 8412364 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.8605. Min Act: -0.1700
Data Index: 2794001 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3605. Min Range: -6.3605
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1499615 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19