Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2133 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.3191. Min Act: -0.1700
Data Index: 2668338 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.2406. Min Act: -0.1700
Data Index: 79260 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.2406. Min Act: -0.1700
Data Index: 3846851 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.2091. Min Act: -0.1700
Data Index: 726232 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.2091. Min Act: -0.1700
Data Index: 1445073 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1619. Min Act: -0.1700
Data Index: 1373617 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1777. Min Act: -0.1700
Data Index: 3160964 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1777. Min Act: -0.1700
Data Index: 2915417 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1619. Min Act: -0.1700
Data Index: 4817681 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1147. Min Act: -0.1700
Data Index: 3032489 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1462. Min Act: -0.1700
Data Index: 7002800 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1147. Min Act: -0.1700
Data Index: 1581613 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1304. Min Act: -0.1700
Data Index: 6375478 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1147. Min Act: -0.1700
Data Index: 6247343 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.1147. Min Act: -0.1700
Data Index: 8770232 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.0989. Min Act: -0.1700
Data Index: 2535656 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.0989. Min Act: -0.1700
Data Index: 5630027 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.0989. Min Act: -0.1700
Data Index: 6510275 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.0989. Min Act: -0.1700
Data Index: 1397184 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3191. Min Range: -3.3191
Max Act: 3.0989. Min Act: -0.1700
Data Index: 7009815 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19