Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5623 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.6742. Min Act: -0.1700
Data Index: 3968825 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.5960. Min Act: -0.1700
Data Index: 732211 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.5960. Min Act: -0.1700
Data Index: 7585035 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.5803. Min Act: -0.1700
Data Index: 5939380 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.5334. Min Act: -0.1700
Data Index: 4129192 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.5490. Min Act: -0.1700
Data Index: 5846623 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.5334. Min Act: -0.1700
Data Index: 1518071 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.5021. Min Act: -0.1700
Data Index: 7558772 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4864. Min Act: -0.1700
Data Index: 2021330 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4864. Min Act: -0.1700
Data Index: 6521864 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4864. Min Act: -0.1700
Data Index: 6538837 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4864. Min Act: -0.1700
Data Index: 1441040 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4707. Min Act: -0.1700
Data Index: 4103398 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4551. Min Act: -0.1700
Data Index: 3813437 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4394. Min Act: -0.1700
Data Index: 6117989 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4394. Min Act: -0.1700
Data Index: 8541593 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4237. Min Act: -0.1700
Data Index: 2295457 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4394. Min Act: -0.1700
Data Index: 1250594 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4237. Min Act: -0.1700
Data Index: 6756249 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6742. Min Range: -3.6742
Max Act: 3.4394. Min Act: -0.1700
Data Index: 2503018 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19