Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4592 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.4736. Min Act: -0.1700
Data Index: 48020 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.4423. Min Act: -0.1700
Data Index: 5586445 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.3798. Min Act: -0.1700
Data Index: 6028578 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.3798. Min Act: -0.1700
Data Index: 8345304 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.3798. Min Act: -0.1700
Data Index: 5963007 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.3173. Min Act: -0.1700
Data Index: 3689865 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2861. Min Act: -0.1700
Data Index: 5182689 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.3173. Min Act: -0.1700
Data Index: 1255822 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2861. Min Act: -0.1700
Data Index: 511116 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2861. Min Act: -0.1700
Data Index: 4654034 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2548. Min Act: -0.1700
Data Index: 2149170 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2548. Min Act: -0.1700
Data Index: 609941 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2548. Min Act: -0.1700
Data Index: 3381097 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2548. Min Act: -0.1700
Data Index: 3614058 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2548. Min Act: -0.1700
Data Index: 8146082 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2236. Min Act: -0.1700
Data Index: 3094748 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.2236. Min Act: -0.1700
Data Index: 4330908 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.1611. Min Act: -0.1700
Data Index: 6537259 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.1923. Min Act: -0.1700
Data Index: 3286105 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4736. Min Range: -6.4736
Max Act: 6.1923. Min Act: -0.1700
Data Index: 4809379 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19