Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3843 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.5087. Min Act: -0.1700
Data Index: 1774031 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.4774. Min Act: -0.1700
Data Index: 2292324 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.4149. Min Act: -0.1691
Data Index: 3418247 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.4462. Min Act: -0.1700
Data Index: 4679730 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.4462. Min Act: -0.1700
Data Index: 4084286 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.4462. Min Act: -0.1700
Data Index: 6820026 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1700
Data Index: 1447616 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1700
Data Index: 8380801 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1699
Data Index: 3683825 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1700
Data Index: 8426006 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1693
Data Index: 962759 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1699
Data Index: 8432695 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1686
Data Index: 8779603 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1700
Data Index: 2352767 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1700
Data Index: 1774027 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3837. Min Act: -0.1700
Data Index: 1902440 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3524. Min Act: -0.1700
Data Index: 415443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3524. Min Act: -0.1698
Data Index: 6929637 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3524. Min Act: -0.1700
Data Index: 1774038 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5087. Min Range: -4.5087
Max Act: 4.3212. Min Act: -0.1700
Data Index: 1161962 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19