Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3531. Min Range: -5.3531
Max Act: 5.3531. Min Act: -0.1700
Data Index: 7891909 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3531. Min Range: -5.3531
Max Act: 5.3218. Min Act: -0.1700
Data Index: 3840213 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3531. Min Range: -5.3531
Max Act: 5.2281. Min Act: -0.1700
Data Index: 8642321 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3531. Min Range: -5.3531
Max Act: 5.1968. Min Act: -0.1700
Data Index: 5746517 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3531. Min Range: -5.3531
Max Act: 5.1656. Min Act: -0.1700
Data Index: 5789432 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3531. Min Range: -5.3531
Max Act: 5.1343. Min Act: -0.1700
Data Index: 8157495 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3531. Min Range: -5.3531
Max Act: 5.0406. Min Act: -0.1700
Data Index: 3310271 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3531. Min Range: -5.3531
Max Act: 5.0406. Min Act: -0.1700
Data Index: 124112 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3531. Min Range: -5.3531
Max Act: 5.0406. Min Act: -0.1700
Data Index: 6797800 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9781. Min Act: -0.1700
Data Index: 5680958 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9781. Min Act: -0.1700
Data Index: 4326565 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9468. Min Act: -0.1700
Data Index: 7227711 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9468. Min Act: -0.1700
Data Index: 6234530 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9468. Min Act: -0.1700
Data Index: 7758436 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9781. Min Act: -0.1700
Data Index: 8141771 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9468. Min Act: -0.1700
Data Index: 181981 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9468. Min Act: -0.1700
Data Index: 7569196 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9781. Min Act: -0.1700
Data Index: 618855 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9156. Min Act: -0.1700
Data Index: 2474108 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3531. Min Range: -5.3531
Max Act: 4.9156. Min Act: -0.1700
Data Index: 7317592 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19