Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.4053. Min Act: -0.1700
Data Index: 4238229 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.2641. Min Act: -0.1700
Data Index: 7406251 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.2169. Min Act: -0.1700
Data Index: 3470803 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.2169. Min Act: -0.1700
Data Index: 2120795 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1697. Min Act: -0.1700
Data Index: 8807387 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1540. Min Act: -0.1700
Data Index: 4537653 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1697. Min Act: -0.1700
Data Index: 2622616 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1067. Min Act: -0.1700
Data Index: 2615326 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1067. Min Act: -0.1700
Data Index: 8646467 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1225. Min Act: -0.1700
Data Index: 7044919 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1067. Min Act: -0.1700
Data Index: 4551569 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1067. Min Act: -0.1700
Data Index: 4535654 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1067. Min Act: -0.1700
Data Index: 2031278 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1067. Min Act: -0.1700
Data Index: 239572 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1067. Min Act: -0.1700
Data Index: 8340901 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.0752. Min Act: -0.1700
Data Index: 1474810 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.0752. Min Act: -0.1700
Data Index: 5127198 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.1067. Min Act: -0.1700
Data Index: 1396320 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.0594. Min Act: -0.1700
Data Index: 116283 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4053. Min Range: -3.4053
Max Act: 3.0752. Min Act: -0.1700
Data Index: 1211129 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19