Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6128 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.5450. Min Act: -0.1700
Data Index: 4084306 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.5137. Min Act: -0.1700
Data Index: 3902662 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.5137. Min Act: -0.1700
Data Index: 2746913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4824. Min Act: -0.1700
Data Index: 3983776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4824. Min Act: -0.1700
Data Index: 8228556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4824. Min Act: -0.1700
Data Index: 4613251 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4824. Min Act: -0.1700
Data Index: 1159809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4510. Min Act: -0.1700
Data Index: 2174182 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4510. Min Act: -0.1700
Data Index: 2555198 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4510. Min Act: -0.1700
Data Index: 5767209 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4510. Min Act: -0.1700
Data Index: 7526424 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4510. Min Act: -0.1700
Data Index: 441502 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4197. Min Act: -0.1700
Data Index: 3398283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4197. Min Act: -0.1700
Data Index: 3299303 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4197. Min Act: -0.1700
Data Index: 7695251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4197. Min Act: -0.1700
Data Index: 7597024 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.3883. Min Act: -0.1700
Data Index: 2916175 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4197. Min Act: -0.1700
Data Index: 2663020 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4197. Min Act: -0.1700
Data Index: 6101764 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5450. Min Range: -3.5450
Max Act: 3.4197. Min Act: -0.1700
Data Index: 4999904 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19