Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 711 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.7281. Min Act: -0.1700
Data Index: 827410 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.7593. Min Act: -0.1700
Data Index: 1546458 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.6656. Min Act: -0.1700
Data Index: 5529731 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.6656. Min Act: -0.1700
Data Index: 1854625 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.6343. Min Act: -0.1700
Data Index: 2901234 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.5718. Min Act: -0.1700
Data Index: 6177392 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.5718. Min Act: -0.1700
Data Index: 8185470 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.5718. Min Act: -0.1700
Data Index: 7831623 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.5718. Min Act: -0.1700
Data Index: 1518642 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.5406. Min Act: -0.1700
Data Index: 1511385 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.5093. Min Act: -0.1700
Data Index: 6602810 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.5093. Min Act: -0.1700
Data Index: 5727640 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.4781. Min Act: -0.1700
Data Index: 7671662 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.4781. Min Act: -0.1700
Data Index: 4982736 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.4781. Min Act: -0.1700
Data Index: 4671312 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.4468. Min Act: -0.1700
Data Index: 5479637 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.4468. Min Act: -0.1700
Data Index: 2557777 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.4156. Min Act: -0.1700
Data Index: 5346626 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.4156. Min Act: -0.1700
Data Index: 7690146 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7593. Min Range: -6.7593
Max Act: 6.4156. Min Act: -0.1700
Data Index: 4671313 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19