Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2298 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.3566. Min Act: -0.1700
Data Index: 5592721 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.3566. Min Act: -0.1700
Data Index: 7462695 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.3254. Min Act: -0.1700
Data Index: 4430023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.3254. Min Act: -0.1700
Data Index: 4893158 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.3254. Min Act: -0.1700
Data Index: 5934929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.3254. Min Act: -0.1700
Data Index: 6484329 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.3254. Min Act: -0.1700
Data Index: 6610752 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.3566. Min Act: -0.1700
Data Index: 7987355 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.3254. Min Act: -0.1700
Data Index: 665055 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2941. Min Act: -0.1700
Data Index: 3945560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2941. Min Act: -0.1700
Data Index: 395754 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2629. Min Act: -0.1700
Data Index: 126786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2629. Min Act: -0.1700
Data Index: 1794537 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2629. Min Act: -0.1700
Data Index: 4368408 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2316. Min Act: -0.1700
Data Index: 4108899 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2316. Min Act: -0.1700
Data Index: 651015 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2316. Min Act: -0.1700
Data Index: 2762575 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2316. Min Act: -0.1700
Data Index: 2954823 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2316. Min Act: -0.1700
Data Index: 1359863 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3566. Min Range: -4.3566
Max Act: 4.2316. Min Act: -0.1700
Data Index: 2954930 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19