Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 840 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 24.2512. Min Range: -24.2512
Max Act: 24.2512. Min Act: -0.1700
Data Index: 7027068 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 24.2512. Min Range: -24.2512
Max Act: 24.1262. Min Act: -0.1700
Data Index: 5894023 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 24.2512. Min Range: -24.2512
Max Act: 24.1262. Min Act: -0.1700
Data Index: 7956481 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 24.2512. Min Range: -24.2512
Max Act: 24.1262. Min Act: -0.1700
Data Index: 5291121 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 24.2512. Min Range: -24.2512
Max Act: 24.0012. Min Act: -0.1700
Data Index: 2602470 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 24.2512. Min Range: -24.2512
Max Act: 24.0012. Min Act: -0.1700
Data Index: 7184637 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 24.2512. Min Range: -24.2512
Max Act: 24.0012. Min Act: -0.1700
Data Index: 7542751 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.8762. Min Act: -0.1700
Data Index: 8109374 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 24.2512. Min Range: -24.2512
Max Act: 24.0012. Min Act: -0.1700
Data Index: 4323889 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 24.2512. Min Range: -24.2512
Max Act: 24.0012. Min Act: -0.1700
Data Index: 701344 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.8762. Min Act: -0.1700
Data Index: 4939726 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.8762. Min Act: -0.1700
Data Index: 4801359 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.8762. Min Act: -0.1700
Data Index: 1628517 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.7512. Min Act: -0.1700
Data Index: 4204677 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.7512. Min Act: -0.1700
Data Index: 401913 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.8762. Min Act: -0.1700
Data Index: 4125228 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.7512. Min Act: -0.1700
Data Index: 4111307 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.8762. Min Act: -0.1700
Data Index: 3793841 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.8762. Min Act: -0.1700
Data Index: 1390265 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 24.2512. Min Range: -24.2512
Max Act: 23.8762. Min Act: -0.1700
Data Index: 1121689 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19