Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 852 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.3206. Min Act: -0.1700
Data Index: 2580160 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.2581. Min Act: -0.1700
Data Index: 7002024 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.2269. Min Act: -0.1700
Data Index: 8430066 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.2269. Min Act: -0.1700
Data Index: 7718314 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1644. Min Act: -0.1700
Data Index: 7405325 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1644. Min Act: -0.1700
Data Index: 2201837 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.0706. Min Act: -0.1700
Data Index: 2510369 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.0081. Min Act: -0.1700
Data Index: 4387204 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.0081. Min Act: -0.1700
Data Index: 2881839 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.9769. Min Act: -0.1700
Data Index: 6461060 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.0081. Min Act: -0.1700
Data Index: 5556094 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.9769. Min Act: -0.1700
Data Index: 3844210 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.9769. Min Act: -0.1700
Data Index: 2000347 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.9456. Min Act: -0.1700
Data Index: 3160589 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.9456. Min Act: -0.1700
Data Index: 3869915 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.9456. Min Act: -0.1700
Data Index: 4228129 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.8831. Min Act: -0.1700
Data Index: 702993 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.8519. Min Act: -0.1700
Data Index: 6610564 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.8831. Min Act: -0.1700
Data Index: 1429333 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3206. Min Range: -5.3206
Max Act: 4.8206. Min Act: -0.1700
Data Index: 2065607 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19