Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.7133. Min Act: -0.1700
Data Index: 2229744 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.5258. Min Act: -0.1700
Data Index: 3875693 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.4321. Min Act: -0.1700
Data Index: 6453006 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.4321. Min Act: -0.1700
Data Index: 6019111 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.4321. Min Act: -0.1700
Data Index: 1904889 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.3696. Min Act: -0.1700
Data Index: 2482670 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.2133. Min Act: -0.1700
Data Index: 869317 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.2133. Min Act: -0.1700
Data Index: 7542482 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.1821. Min Act: -0.1700
Data Index: 7935400 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.1508. Min Act: -0.1700
Data Index: 1933675 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.1508. Min Act: -0.1700
Data Index: 5933089 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.1508. Min Act: -0.1700
Data Index: 3355580 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.1196. Min Act: -0.1700
Data Index: 2533919 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.1196. Min Act: -0.1700
Data Index: 6137018 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.0883. Min Act: -0.1700
Data Index: 1172520 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.0258. Min Act: -0.1700
Data Index: 5933080 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.0571. Min Act: -0.1700
Data Index: 7542483 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.0258. Min Act: -0.1700
Data Index: 2100079 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.0258. Min Act: -0.1700
Data Index: 3656803 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7133. Min Range: -6.7133
Max Act: 6.0258. Min Act: -0.1700
Data Index: 4045753 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19