Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8786. Min Act: -0.1700
Data Index: 3379565 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8786. Min Act: -0.1700
Data Index: 1363243 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8786. Min Act: -0.1700
Data Index: 4143350 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8786. Min Act: -0.1700
Data Index: 6414332 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8309. Min Act: -0.1700
Data Index: 1971036 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8627. Min Act: -0.1700
Data Index: 2721167 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8627. Min Act: -0.1700
Data Index: 4280084 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8309. Min Act: -0.1700
Data Index: 211397 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8309. Min Act: -0.1700
Data Index: 4548976 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8309. Min Act: -0.1700
Data Index: 5351499 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.7991. Min Act: -0.1700
Data Index: 5826398 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8150. Min Act: -0.1700
Data Index: 5511804 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8309. Min Act: -0.1700
Data Index: 882753 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.8150. Min Act: -0.1700
Data Index: 2397315 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.7353. Min Act: -0.1700
Data Index: 7855616 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.7832. Min Act: -0.1700
Data Index: 8369097 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.7513. Min Act: -0.1700
Data Index: 5053308 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.7832. Min Act: -0.1700
Data Index: 2626711 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.7672. Min Act: -0.1700
Data Index: 42669 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8786. Min Range: -2.8786
Max Act: 2.7672. Min Act: -0.1700
Data Index: 5277984 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19