Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1966 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.5389. Min Act: -0.1700
Data Index: 5557682 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.5076. Min Act: -0.1700
Data Index: 2065933 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4763. Min Act: -0.1700
Data Index: 6577793 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.4293. Min Act: -0.1700
Data Index: 3804755 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3979. Min Act: -0.1700
Data Index: 2321968 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3979. Min Act: -0.1700
Data Index: 791861 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3509. Min Act: -0.1700
Data Index: 2430810 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3509. Min Act: -0.1700
Data Index: 4002118 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3665. Min Act: -0.1700
Data Index: 6084833 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3352. Min Act: -0.1700
Data Index: 2172751 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3195. Min Act: -0.1700
Data Index: 1692327 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3038. Min Act: -0.1700
Data Index: 4105067 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3195. Min Act: -0.1700
Data Index: 7127686 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3195. Min Act: -0.1700
Data Index: 5064319 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.2881. Min Act: -0.1700
Data Index: 3071180 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.3038. Min Act: -0.1700
Data Index: 8421674 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.2724. Min Act: -0.1700
Data Index: 5313580 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.2724. Min Act: -0.1700
Data Index: 1960204 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.2724. Min Act: -0.1700
Data Index: 294869 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5389. Min Range: -3.5389
Max Act: 3.2410. Min Act: -0.1700
Data Index: 6450247 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19