Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.5986. Min Act: -0.1700
Data Index: 4489758 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.5049. Min Act: -0.1700
Data Index: 7383733 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.4424. Min Act: -0.1700
Data Index: 2846412 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.4424. Min Act: -0.1700
Data Index: 3726391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.4111. Min Act: -0.1700
Data Index: 3294879 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.3799. Min Act: -0.1700
Data Index: 585094 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.3486. Min Act: -0.1700
Data Index: 3564153 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.3486. Min Act: -0.1700
Data Index: 2174537 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.3173. Min Act: -0.1700
Data Index: 1081224 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.3173. Min Act: -0.1700
Data Index: 1767338 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.2861. Min Act: -0.1700
Data Index: 5240659 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.2861. Min Act: -0.1700
Data Index: 1436370 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.2861. Min Act: -0.1700
Data Index: 5164467 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.2861. Min Act: -0.1700
Data Index: 993036 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.2548. Min Act: -0.1700
Data Index: 4487712 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.2236. Min Act: -0.1700
Data Index: 2781013 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.2236. Min Act: -0.1700
Data Index: 4510123 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.2236. Min Act: -0.1700
Data Index: 466274 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.1923. Min Act: -0.1700
Data Index: 4706973 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5986. Min Range: -4.5986
Max Act: 4.1923. Min Act: -0.1700
Data Index: 2103693 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19