Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3507. Min Range: -1.3507
Max Act: 1.3507. Min Act: -0.1700
Data Index: 4648097 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3507. Min Range: -1.3507
Max Act: 1.2536. Min Act: -0.1700
Data Index: 7624595 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3507. Min Range: -1.3507
Max Act: 1.1920. Min Act: -0.1700
Data Index: 1602732 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3507. Min Range: -1.3507
Max Act: 1.1304. Min Act: -0.1700
Data Index: 5364583 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3507. Min Range: -1.3507
Max Act: 1.0342. Min Act: -0.1700
Data Index: 1269307 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9995. Min Act: -0.1700
Data Index: 4551357 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9908. Min Act: -0.1700
Data Index: 5298749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9908. Min Act: -0.1700
Data Index: 1816190 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9908. Min Act: -0.1700
Data Index: 2323580 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9562. Min Act: -0.1700
Data Index: 5009396 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9735. Min Act: -0.1700
Data Index: 3618323 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9476. Min Act: -0.1700
Data Index: 3249481 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9476. Min Act: -0.1700
Data Index: 2482601 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9218. Min Act: -0.1700
Data Index: 2370287 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9218. Min Act: -0.1700
Data Index: 8335192 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9132. Min Act: -0.1700
Data Index: 5009400 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9218. Min Act: -0.1700
Data Index: 291874 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9132. Min Act: -0.1700
Data Index: 5009397 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.9046. Min Act: -0.1700
Data Index: 7588008 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3507. Min Range: -1.3507
Max Act: 0.8961. Min Act: -0.1700
Data Index: 8011642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19