Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5453 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.6900. Min Act: -0.1700
Data Index: 7533152 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.6275. Min Act: -0.1700
Data Index: 464570 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.6275. Min Act: -0.1700
Data Index: 8392913 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.5025. Min Act: -0.1700
Data Index: 1811242 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.5338. Min Act: -0.1700
Data Index: 6287702 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.5025. Min Act: -0.1700
Data Index: 5956537 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.5025. Min Act: -0.1700
Data Index: 4594792 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.4713. Min Act: -0.1700
Data Index: 5361683 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.4400. Min Act: -0.1700
Data Index: 4015052 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.4400. Min Act: -0.1700
Data Index: 2643644 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.4713. Min Act: -0.1700
Data Index: 3876228 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.4088. Min Act: -0.1700
Data Index: 1677416 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.3775. Min Act: -0.1700
Data Index: 4020938 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.3775. Min Act: -0.1700
Data Index: 3296496 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.3463. Min Act: -0.1700
Data Index: 8714270 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.3463. Min Act: -0.1700
Data Index: 5581917 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.3463. Min Act: -0.1700
Data Index: 2963212 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.3463. Min Act: -0.1700
Data Index: 4883716 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.3463. Min Act: -0.1700
Data Index: 7561096 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6900. Min Range: -5.6900
Max Act: 5.3150. Min Act: -0.1700
Data Index: 16449 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19