Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 225 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.2887. Min Act: -0.1700
Data Index: 5684432 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.2262. Min Act: -0.1700
Data Index: 1354347 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.1325. Min Act: -0.1700
Data Index: 1370392 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.0700. Min Act: -0.1700
Data Index: 6652567 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.1012. Min Act: -0.1700
Data Index: 6042188 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.1012. Min Act: -0.1700
Data Index: 7406642 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.1012. Min Act: -0.1700
Data Index: 390348 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.1012. Min Act: -0.1700
Data Index: 866356 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.0075. Min Act: -0.1700
Data Index: 4921468 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.0075. Min Act: -0.1700
Data Index: 8527382 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2887. Min Range: -5.2887
Max Act: 5.0075. Min Act: -0.1700
Data Index: 6091603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2887. Min Range: -5.2887
Max Act: 4.9762. Min Act: -0.1700
Data Index: 5436689 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2887. Min Range: -5.2887
Max Act: 4.9762. Min Act: -0.1700
Data Index: 8066766 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2887. Min Range: -5.2887
Max Act: 4.9762. Min Act: -0.1700
Data Index: 6947339 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2887. Min Range: -5.2887
Max Act: 4.9762. Min Act: -0.1700
Data Index: 2669778 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2887. Min Range: -5.2887
Max Act: 4.9450. Min Act: -0.1700
Data Index: 2984915 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2887. Min Range: -5.2887
Max Act: 4.9450. Min Act: -0.1700
Data Index: 1942961 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2887. Min Range: -5.2887
Max Act: 4.9137. Min Act: -0.1700
Data Index: 129454 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2887. Min Range: -5.2887
Max Act: 4.9137. Min Act: -0.1700
Data Index: 537423 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2887. Min Range: -5.2887
Max Act: 4.9450. Min Act: -0.1700
Data Index: 8349668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19