Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1323 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0258. Min Range: -5.0258
Max Act: 5.0258. Min Act: -0.1700
Data Index: 4391621 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0258. Min Range: -5.0258
Max Act: 5.0258. Min Act: -0.1700
Data Index: 92930 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.9946. Min Act: -0.1700
Data Index: 745762 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.9633. Min Act: -0.1700
Data Index: 7558588 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.9008. Min Act: -0.1700
Data Index: 3486449 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.9008. Min Act: -0.1700
Data Index: 3274490 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.8383. Min Act: -0.1700
Data Index: 3028901 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.8696. Min Act: -0.1700
Data Index: 4984015 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.8071. Min Act: -0.1700
Data Index: 2439212 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.8071. Min Act: -0.1700
Data Index: 2440496 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.8071. Min Act: -0.1700
Data Index: 5129728 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.8071. Min Act: -0.1700
Data Index: 174823 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.8071. Min Act: -0.1700
Data Index: 720642 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.8071. Min Act: -0.1700
Data Index: 3838702 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.7758. Min Act: -0.1700
Data Index: 643161 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.7758. Min Act: -0.1700
Data Index: 4806560 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.7758. Min Act: -0.1700
Data Index: 4984020 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.7758. Min Act: -0.1700
Data Index: 1026035 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.7758. Min Act: -0.1700
Data Index: 669984 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0258. Min Range: -5.0258
Max Act: 4.7758. Min Act: -0.1700
Data Index: 4412999 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19