Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4515 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.5605. Min Act: -0.1700
Data Index: 8755684 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.5605. Min Act: -0.1700
Data Index: 8343776 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.5293. Min Act: -0.1700
Data Index: 4608582 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4668. Min Act: -0.1700
Data Index: 3684639 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4980. Min Act: -0.1700
Data Index: 8551117 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4980. Min Act: -0.1700
Data Index: 530045 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4355. Min Act: -0.1700
Data Index: 7558021 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4355. Min Act: -0.1700
Data Index: 2298952 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4043. Min Act: -0.1700
Data Index: 3720798 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4043. Min Act: -0.1700
Data Index: 7290737 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4043. Min Act: -0.1700
Data Index: 980178 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4043. Min Act: -0.1700
Data Index: 7019502 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.3730. Min Act: -0.1700
Data Index: 5195810 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.3730. Min Act: -0.1700
Data Index: 8509335 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.3730. Min Act: -0.1700
Data Index: 808829 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4043. Min Act: -0.1700
Data Index: 7642905 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.3730. Min Act: -0.1695
Data Index: 1314520 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.4043. Min Act: -0.1700
Data Index: 1464343 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.3418. Min Act: -0.1700
Data Index: 2244133 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.3105. Min Act: -0.1700
Data Index: 8361538 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19