Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8559. Min Act: -0.1700
Data Index: 2903422 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8559. Min Act: -0.1700
Data Index: 1904475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8247. Min Act: -0.1700
Data Index: 1023031 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.7934. Min Act: -0.1700
Data Index: 4433409 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8247. Min Act: -0.1700
Data Index: 1924401 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8247. Min Act: -0.1700
Data Index: 8285107 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8247. Min Act: -0.1700
Data Index: 8030882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8247. Min Act: -0.1700
Data Index: 604246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8247. Min Act: -0.1700
Data Index: 2907381 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8247. Min Act: -0.1700
Data Index: 2857306 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.7934. Min Act: -0.1700
Data Index: 2616823 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8247. Min Act: -0.1700
Data Index: 8029275 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.8247. Min Act: -0.1700
Data Index: 1983446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.7621. Min Act: -0.1700
Data Index: 618425 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.7934. Min Act: -0.1700
Data Index: 4087634 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.7934. Min Act: -0.1700
Data Index: 5156537 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.7934. Min Act: -0.1699
Data Index: 5485200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.7934. Min Act: -0.1700
Data Index: 6037133 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.7934. Min Act: -0.1700
Data Index: 7311568 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8559. Min Range: -3.8559
Max Act: 3.7934. Min Act: -0.1700
Data Index: 7945815 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19