Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5010 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0561. Min Range: -7.0561
Max Act: 7.0561. Min Act: -0.1700
Data Index: 7529027 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.8686. Min Act: -0.1700
Data Index: 8174107 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.6811. Min Act: -0.1700
Data Index: 6112573 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.5873. Min Act: -0.1700
Data Index: 2359650 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.4936. Min Act: -0.1700
Data Index: 7528649 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.4311. Min Act: -0.1700
Data Index: 187989 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.3998. Min Act: -0.1700
Data Index: 3925981 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.3373. Min Act: -0.1700
Data Index: 2413654 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.3373. Min Act: -0.1700
Data Index: 8651240 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.3061. Min Act: -0.1700
Data Index: 4094945 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.3061. Min Act: -0.1700
Data Index: 4229836 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.3061. Min Act: -0.1700
Data Index: 5931571 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.3061. Min Act: -0.1700
Data Index: 746817 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.3061. Min Act: -0.1700
Data Index: 3794563 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.2748. Min Act: -0.1700
Data Index: 5557743 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.3061. Min Act: -0.1700
Data Index: 7911704 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.2436. Min Act: -0.1700
Data Index: 2257271 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.2123. Min Act: -0.1700
Data Index: 4755231 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.2123. Min Act: -0.1700
Data Index: 2386053 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0561. Min Range: -7.0561
Max Act: 6.1811. Min Act: -0.1700
Data Index: 2144174 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19