Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.4992. Min Act: -0.1700
Data Index: 2330330 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3738. Min Act: -0.1700
Data Index: 8338354 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3738. Min Act: -0.1700
Data Index: 5139418 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3581. Min Act: -0.1700
Data Index: 4289483 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3424. Min Act: -0.1700
Data Index: 342055 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3424. Min Act: -0.1700
Data Index: 4662433 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3267. Min Act: -0.1700
Data Index: 2659010 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3267. Min Act: -0.1700
Data Index: 5775261 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3110. Min Act: -0.1700
Data Index: 2491383 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3110. Min Act: -0.1700
Data Index: 8424641 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3110. Min Act: -0.1700
Data Index: 296155 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.3110. Min Act: -0.1700
Data Index: 3457595 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.2953. Min Act: -0.1700
Data Index: 5022459 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.2953. Min Act: -0.1700
Data Index: 5841045 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.2953. Min Act: -0.1700
Data Index: 4761928 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.2953. Min Act: -0.1700
Data Index: 7535223 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.2639. Min Act: -0.1700
Data Index: 99974 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.2796. Min Act: -0.1700
Data Index: 6025400 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.2796. Min Act: -0.1700
Data Index: 4010668 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4992. Min Range: -3.4992
Max Act: 3.2639. Min Act: -0.1700
Data Index: 6824291 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19