Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3917 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.5310. Min Act: -0.1700
Data Index: 2137427 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.4998. Min Act: -0.1700
Data Index: 8591538 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.4998. Min Act: -0.1700
Data Index: 2137438 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.4685. Min Act: -0.1700
Data Index: 164912 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.4685. Min Act: -0.1700
Data Index: 5453852 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.4373. Min Act: -0.1700
Data Index: 7007939 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.4373. Min Act: -0.1700
Data Index: 1447218 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.4060. Min Act: -0.1700
Data Index: 6570218 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.4060. Min Act: -0.1700
Data Index: 7645462 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3748. Min Act: -0.1700
Data Index: 2575787 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3435. Min Act: -0.1700
Data Index: 5205330 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3435. Min Act: -0.1700
Data Index: 7045384 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3435. Min Act: -0.1700
Data Index: 6536035 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3123. Min Act: -0.1700
Data Index: 141780 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.2810. Min Act: -0.1700
Data Index: 1193351 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3123. Min Act: -0.1700
Data Index: 4309304 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3123. Min Act: -0.1700
Data Index: 2575798 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3123. Min Act: -0.1700
Data Index: 2575782 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3123. Min Act: -0.1700
Data Index: 684538 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5310. Min Range: -5.5310
Max Act: 5.3123. Min Act: -0.1700
Data Index: 2831961 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19