Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1967 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2984. Min Range: -5.2984
Max Act: 5.2984. Min Act: -0.1700
Data Index: 4322229 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2984. Min Range: -5.2984
Max Act: 5.1422. Min Act: -0.1700
Data Index: 84896 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.9859. Min Act: -0.1700
Data Index: 4033436 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.9547. Min Act: -0.1700
Data Index: 1591568 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.9547. Min Act: -0.1700
Data Index: 2326345 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.9859. Min Act: -0.1700
Data Index: 1799589 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.9234. Min Act: -0.1700
Data Index: 4364692 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.9234. Min Act: -0.1700
Data Index: 7183497 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.8922. Min Act: -0.1700
Data Index: 2545388 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.8922. Min Act: -0.1700
Data Index: 4688195 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.8609. Min Act: -0.1700
Data Index: 5276583 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.8609. Min Act: -0.1700
Data Index: 6637661 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.8609. Min Act: -0.1700
Data Index: 1063898 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.8297. Min Act: -0.1700
Data Index: 5249834 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.8297. Min Act: -0.1700
Data Index: 4138677 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.7984. Min Act: -0.1700
Data Index: 3001862 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.8297. Min Act: -0.1700
Data Index: 805134 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.7984. Min Act: -0.1700
Data Index: 2230074 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.7984. Min Act: -0.1700
Data Index: 1427784 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2984. Min Range: -5.2984
Max Act: 4.8297. Min Act: -0.1700
Data Index: 3109071 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19