Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1310 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.6337. Min Act: -0.1700
Data Index: 8525532 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.5087. Min Act: -0.1699
Data Index: 3353033 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.4775. Min Act: -0.1700
Data Index: 4260636 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.4775. Min Act: -0.1700
Data Index: 3865682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.4775. Min Act: -0.1700
Data Index: 2026078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.4775. Min Act: -0.1700
Data Index: 3491966 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.4149. Min Act: -0.1700
Data Index: 4140587 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.4149. Min Act: -0.1700
Data Index: 542046 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.4149. Min Act: -0.1700
Data Index: 5188926 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3837. Min Act: -0.1700
Data Index: 5897861 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3837. Min Act: -0.1700
Data Index: 2531959 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3837. Min Act: -0.1700
Data Index: 7073213 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3837. Min Act: -0.1700
Data Index: 6811554 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3524. Min Act: -0.1700
Data Index: 1878670 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3524. Min Act: -0.1700
Data Index: 1335016 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3837. Min Act: -0.1700
Data Index: 1864706 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3212. Min Act: -0.1700
Data Index: 8461753 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3524. Min Act: -0.1700
Data Index: 7566755 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3212. Min Act: -0.1700
Data Index: 5693156 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6337. Min Range: -4.6337
Max Act: 4.3212. Min Act: -0.1700
Data Index: 2523277 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19