Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4403 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.4638. Min Act: -0.1700
Data Index: 7656508 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.2763. Min Act: -0.1700
Data Index: 945560 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.2450. Min Act: -0.1700
Data Index: 8213434 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.1825. Min Act: -0.1700
Data Index: 1610116 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.1825. Min Act: -0.1700
Data Index: 8350164 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.0575. Min Act: -0.1700
Data Index: 1635227 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.0888. Min Act: -0.1700
Data Index: 5687289 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.1200. Min Act: -0.1700
Data Index: 2635260 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.0263. Min Act: -0.1700
Data Index: 7626616 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4638. Min Range: -7.4638
Max Act: 7.0263. Min Act: -0.1700
Data Index: 6342250 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9638. Min Act: -0.1700
Data Index: 3344303 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9950. Min Act: -0.1700
Data Index: 4941748 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9950. Min Act: -0.1700
Data Index: 1489252 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9638. Min Act: -0.1700
Data Index: 5499243 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9638. Min Act: -0.1700
Data Index: 2291361 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9638. Min Act: -0.1700
Data Index: 8338491 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9638. Min Act: -0.1700
Data Index: 2110868 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9325. Min Act: -0.1700
Data Index: 2489009 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9013. Min Act: -0.1700
Data Index: 308406 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4638. Min Range: -7.4638
Max Act: 6.9013. Min Act: -0.1700
Data Index: 5953471 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19