Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1885 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2612. Min Range: -4.2612
Max Act: 4.2612. Min Act: -0.1700
Data Index: 6735118 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2612. Min Range: -4.2612
Max Act: 4.1674. Min Act: -0.1700
Data Index: 4251935 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2612. Min Range: -4.2612
Max Act: 4.1361. Min Act: -0.1700
Data Index: 554117 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2612. Min Range: -4.2612
Max Act: 4.0424. Min Act: -0.1700
Data Index: 4894644 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2612. Min Range: -4.2612
Max Act: 4.0424. Min Act: -0.1700
Data Index: 3376903 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.9798. Min Act: -0.1700
Data Index: 7955227 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.9798. Min Act: -0.1700
Data Index: 6437183 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.9798. Min Act: -0.1700
Data Index: 5571692 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.9798. Min Act: -0.1700
Data Index: 4543320 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.9486. Min Act: -0.1700
Data Index: 394410 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.9173. Min Act: -0.1700
Data Index: 6454529 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8861. Min Act: -0.1700
Data Index: 8703217 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8861. Min Act: -0.1700
Data Index: 6333591 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.9173. Min Act: -0.1700
Data Index: 3319018 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8861. Min Act: -0.1700
Data Index: 6613731 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8861. Min Act: -0.1700
Data Index: 3049638 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8861. Min Act: -0.1700
Data Index: 4790281 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8548. Min Act: -0.1700
Data Index: 1451389 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8235. Min Act: -0.1700
Data Index: 913990 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8548. Min Act: -0.1700
Data Index: 6577117 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19