Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1137 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.3218. Min Act: -0.1700
Data Index: 6149353 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1968. Min Act: -0.1700
Data Index: 3873303 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.2280. Min Act: -0.1700
Data Index: 8613484 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1655. Min Act: -0.1700
Data Index: 5298620 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1343. Min Act: -0.1700
Data Index: 5700723 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1343. Min Act: -0.1700
Data Index: 6628461 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1343. Min Act: -0.1700
Data Index: 584972 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1343. Min Act: -0.1700
Data Index: 2429938 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1030. Min Act: -0.1700
Data Index: 3950007 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1030. Min Act: -0.1700
Data Index: 3198184 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1030. Min Act: -0.1700
Data Index: 8641795 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.0718. Min Act: -0.1700
Data Index: 4856549 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.0718. Min Act: -0.1700
Data Index: 7892225 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.0718. Min Act: -0.1700
Data Index: 276923 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1030. Min Act: -0.1700
Data Index: 5723332 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.1030. Min Act: -0.1700
Data Index: 5144671 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.0718. Min Act: -0.1700
Data Index: 2073947 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.0718. Min Act: -0.1700
Data Index: 1610673 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.0718. Min Act: -0.1700
Data Index: 4119717 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3218. Min Range: -6.3218
Max Act: 6.0405. Min Act: -0.1700
Data Index: 1804742 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19