Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2424. Min Act: -0.1700
Data Index: 8285055 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2424. Min Act: -0.1700
Data Index: 5188022 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2424. Min Act: -0.1700
Data Index: 3812931 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2424. Min Act: -0.1699
Data Index: 626215 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2424. Min Act: -0.1700
Data Index: 5849126 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2424. Min Act: -0.1699
Data Index: 5680252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2112. Min Act: -0.1700
Data Index: 2623882 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2112. Min Act: -0.1700
Data Index: 7809964 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.2112. Min Act: -0.1700
Data Index: 6903308 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1487. Min Act: -0.1700
Data Index: 2666562 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1799. Min Act: -0.1700
Data Index: 100010 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1799. Min Act: -0.1700
Data Index: 3603342 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1799. Min Act: -0.1699
Data Index: 5062516 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1799. Min Act: -0.1700
Data Index: 3679867 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1174. Min Act: -0.1700
Data Index: 1944346 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1174. Min Act: -0.1699
Data Index: 1025349 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1174. Min Act: -0.1700
Data Index: 8048125 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1174. Min Act: -0.1700
Data Index: 6278444 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.0862. Min Act: -0.1700
Data Index: 6316646 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2424. Min Range: -6.2424
Max Act: 6.1174. Min Act: -0.1700
Data Index: 1793726 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19