Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2819 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0529. Min Range: -10.0529
Max Act: 10.0529. Min Act: -0.1700
Data Index: 861024 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0529. Min Range: -10.0529
Max Act: 9.6779. Min Act: -0.1700
Data Index: 4170241 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0529. Min Range: -10.0529
Max Act: 9.6779. Min Act: -0.1700
Data Index: 5810189 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0529. Min Range: -10.0529
Max Act: 9.0529. Min Act: -0.1700
Data Index: 8030557 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.9904. Min Act: -0.1700
Data Index: 4295705 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.9904. Min Act: -0.1700
Data Index: 4048535 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.8029. Min Act: -0.1700
Data Index: 3715615 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.8654. Min Act: -0.1700
Data Index: 5227741 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.7404. Min Act: -0.1700
Data Index: 7783354 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.7404. Min Act: -0.1700
Data Index: 5870514 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.6154. Min Act: -0.1700
Data Index: 1594032 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.6154. Min Act: -0.1700
Data Index: 8191046 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.5529. Min Act: -0.1700
Data Index: 1198457 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.4904. Min Act: -0.1700
Data Index: 5891042 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.4279. Min Act: -0.1700
Data Index: 7503057 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.4279. Min Act: -0.1700
Data Index: 933645 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.4279. Min Act: -0.1700
Data Index: 6430082 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.3654. Min Act: -0.1700
Data Index: 432518 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.3342. Min Act: -0.1700
Data Index: 534622 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0529. Min Range: -10.0529
Max Act: 8.3654. Min Act: -0.1700
Data Index: 1226056 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19