Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2498. Min Range: -8.2498
Max Act: 8.2498. Min Act: -0.1700
Data Index: 1901323 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.9998. Min Act: -0.1700
Data Index: 7973828 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.8748. Min Act: -0.1700
Data Index: 6298357 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.8748. Min Act: -0.1700
Data Index: 2549363 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.8748. Min Act: -0.1700
Data Index: 7240879 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.8123. Min Act: -0.1700
Data Index: 2075845 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.8123. Min Act: -0.1700
Data Index: 8680178 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.6873. Min Act: -0.1700
Data Index: 7051521 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.6873. Min Act: -0.1700
Data Index: 1072928 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.6248. Min Act: -0.1700
Data Index: 3707949 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.6873. Min Act: -0.1700
Data Index: 2187902 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.6248. Min Act: -0.1700
Data Index: 8613171 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.6248. Min Act: -0.1700
Data Index: 8680179 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.5623. Min Act: -0.1700
Data Index: 6798092 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.5623. Min Act: -0.1700
Data Index: 4619475 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.5623. Min Act: -0.1700
Data Index: 2986567 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.5623. Min Act: -0.1700
Data Index: 1940280 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.4998. Min Act: -0.1700
Data Index: 4557679 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.4998. Min Act: -0.1700
Data Index: 5665094 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2498. Min Range: -8.2498
Max Act: 7.4686. Min Act: -0.1700
Data Index: 7764814 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19