Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4208 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.7577. Min Act: -0.1700
Data Index: 3147489 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.7577. Min Act: -0.1700
Data Index: 4223925 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.7577. Min Act: -0.1700
Data Index: 3401955 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.7577. Min Act: -0.1700
Data Index: 1634081 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.7265. Min Act: -0.1700
Data Index: 1133507 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.7265. Min Act: -0.1700
Data Index: 844719 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6952. Min Act: -0.1700
Data Index: 363330 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6952. Min Act: -0.1700
Data Index: 2267793 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6640. Min Act: -0.1700
Data Index: 5664956 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6952. Min Act: -0.1700
Data Index: 5985070 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6640. Min Act: -0.1700
Data Index: 4248928 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6640. Min Act: -0.1700
Data Index: 1859259 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6640. Min Act: -0.1700
Data Index: 6528844 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6640. Min Act: -0.1700
Data Index: 3705860 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6952. Min Act: -0.1700
Data Index: 6205607 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6640. Min Act: -0.1700
Data Index: 3405261 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6640. Min Act: -0.1700
Data Index: 4261408 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6640. Min Act: -0.1700
Data Index: 4261407 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6640. Min Act: -0.1700
Data Index: 3211571 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7577. Min Range: -4.7577
Max Act: 4.6327. Min Act: -0.1700
Data Index: 3816623 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19