Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2752 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.4518. Min Act: -0.1700
Data Index: 8340096 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.4342. Min Act: -0.1689
Data Index: 3246644 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.3461. Min Act: -0.1676
Data Index: 4643842 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.3461. Min Act: -0.1700
Data Index: 8013096 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.3461. Min Act: -0.1699
Data Index: 3697109 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.3284. Min Act: -0.1699
Data Index: 518537 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2932. Min Act: -0.1700
Data Index: 2336475 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2932. Min Act: -0.1700
Data Index: 6815964 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2755. Min Act: -0.1678
Data Index: 323912 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2755. Min Act: -0.1691
Data Index: 5757908 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2403. Min Act: -0.1698
Data Index: 6405544 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2403. Min Act: -0.1700
Data Index: 2247207 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2403. Min Act: -0.1691
Data Index: 4453512 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2403. Min Act: -0.1624
Data Index: 2021815 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2403. Min Act: -0.1700
Data Index: 8467475 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2403. Min Act: -0.1679
Data Index: 933107 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2403. Min Act: -0.1411
Data Index: 1944227 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2226. Min Act: -0.1700
Data Index: 3279488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2226. Min Act: -0.1486
Data Index: 3314454 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4518. Min Range: -1.4518
Max Act: 1.2050. Min Act: -0.1700
Data Index: 6779680 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19