Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3713 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.6037. Min Act: -0.1700
Data Index: 2092290 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.4787. Min Act: -0.1700
Data Index: 1749398 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.4475. Min Act: -0.1700
Data Index: 5907905 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.4162. Min Act: -0.1700
Data Index: 4468440 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.2912. Min Act: -0.1700
Data Index: 8526209 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.2600. Min Act: -0.1700
Data Index: 5503684 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.2600. Min Act: -0.1700
Data Index: 7980744 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.2912. Min Act: -0.1700
Data Index: 4508833 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1975. Min Act: -0.1700
Data Index: 5679488 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1975. Min Act: -0.1700
Data Index: 1928307 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1662. Min Act: -0.1700
Data Index: 4090191 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1975. Min Act: -0.1700
Data Index: 2251956 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1975. Min Act: -0.1700
Data Index: 6117399 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1662. Min Act: -0.1700
Data Index: 220226 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1662. Min Act: -0.1700
Data Index: 4802137 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1350. Min Act: -0.1700
Data Index: 2327206 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1037. Min Act: -0.1700
Data Index: 6007707 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1350. Min Act: -0.1700
Data Index: 6411317 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1037. Min Act: -0.1700
Data Index: 1315814 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6037. Min Range: -5.6037
Max Act: 5.1037. Min Act: -0.1700
Data Index: 928359 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19