Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.8294. Min Act: -0.1700
Data Index: 2786247 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.8294. Min Act: -0.1700
Data Index: 4834158 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.7982. Min Act: -0.1700
Data Index: 3443037 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.7200. Min Act: -0.1700
Data Index: 5330420 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.6730. Min Act: -0.1700
Data Index: 6559855 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5791. Min Act: -0.1700
Data Index: 1466420 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5948. Min Act: -0.1700
Data Index: 1926403 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5948. Min Act: -0.1700
Data Index: 516929 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5478. Min Act: -0.1700
Data Index: 1069876 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5322. Min Act: -0.1700
Data Index: 8162370 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5165. Min Act: -0.1700
Data Index: 5241686 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5165. Min Act: -0.1700
Data Index: 7468129 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5008. Min Act: -0.1700
Data Index: 627814 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5008. Min Act: -0.1700
Data Index: 2906579 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5165. Min Act: -0.1700
Data Index: 6728017 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5322. Min Act: -0.1700
Data Index: 3791925 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5322. Min Act: -0.1700
Data Index: 5583956 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.4695. Min Act: -0.1700
Data Index: 1126809 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5008. Min Act: -0.1700
Data Index: 2200111 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8294. Min Range: -3.8294
Max Act: 3.5008. Min Act: -0.1700
Data Index: 1169865 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19