Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5312 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0981. Min Range: -4.0981
Max Act: 4.0981. Min Act: -0.1700
Data Index: 7223554 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0981. Min Range: -4.0981
Max Act: 4.0043. Min Act: -0.1700
Data Index: 7752278 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.9418. Min Act: -0.1700
Data Index: 8063167 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.9418. Min Act: -0.1700
Data Index: 907511 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.9105. Min Act: -0.1700
Data Index: 1038035 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.9105. Min Act: -0.1700
Data Index: 5078429 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.9105. Min Act: -0.1700
Data Index: 2201236 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.8167. Min Act: -0.1700
Data Index: 3142552 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.8167. Min Act: -0.1700
Data Index: 5078428 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7854. Min Act: -0.1700
Data Index: 6622263 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7541. Min Act: -0.1700
Data Index: 4695441 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7854. Min Act: -0.1700
Data Index: 2416171 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7541. Min Act: -0.1700
Data Index: 2249399 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7541. Min Act: -0.1700
Data Index: 93775 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7541. Min Act: -0.1700
Data Index: 8572260 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7541. Min Act: -0.1700
Data Index: 8214722 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7229. Min Act: -0.1700
Data Index: 7579756 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7229. Min Act: -0.1700
Data Index: 3121789 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7229. Min Act: -0.1700
Data Index: 46732 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0981. Min Range: -4.0981
Max Act: 3.7229. Min Act: -0.1700
Data Index: 1417356 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19