Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 926 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5623. Min Range: -9.5623
Max Act: 9.5623. Min Act: -0.1700
Data Index: 5295517 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5623. Min Range: -9.5623
Max Act: 9.5623. Min Act: -0.1700
Data Index: 4440775 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5623. Min Range: -9.5623
Max Act: 9.4998. Min Act: -0.1700
Data Index: 4250645 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5623. Min Range: -9.5623
Max Act: 9.3123. Min Act: -0.1700
Data Index: 8515777 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5623. Min Range: -9.5623
Max Act: 9.3748. Min Act: -0.1700
Data Index: 7366259 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5623. Min Range: -9.5623
Max Act: 9.1873. Min Act: -0.1700
Data Index: 5408908 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5623. Min Range: -9.5623
Max Act: 9.1248. Min Act: -0.1700
Data Index: 1210222 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5623. Min Range: -9.5623
Max Act: 9.1248. Min Act: -0.1700
Data Index: 5822741 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5623. Min Range: -9.5623
Max Act: 9.1248. Min Act: -0.1700
Data Index: 5060453 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.9998. Min Act: -0.1700
Data Index: 587892 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.9998. Min Act: -0.1700
Data Index: 5153275 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.9998. Min Act: -0.1700
Data Index: 2649322 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.9373. Min Act: -0.1700
Data Index: 2545446 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.9373. Min Act: -0.1700
Data Index: 12900 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.9373. Min Act: -0.1700
Data Index: 5165937 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.9373. Min Act: -0.1700
Data Index: 5915489 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.9373. Min Act: -0.1700
Data Index: 5294211 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.8748. Min Act: -0.1700
Data Index: 7864129 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.8748. Min Act: -0.1700
Data Index: 3634287 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5623. Min Range: -9.5623
Max Act: 8.8748. Min Act: -0.1700
Data Index: 3184500 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19