Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1958. Min Range: -4.1958
Max Act: 4.1958. Min Act: -0.1700
Data Index: 8245979 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1958. Min Range: -4.1958
Max Act: 4.1333. Min Act: -0.1700
Data Index: 7646557 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1958. Min Range: -4.1958
Max Act: 4.1333. Min Act: -0.1700
Data Index: 3413549 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1958. Min Range: -4.1958
Max Act: 4.1333. Min Act: -0.1700
Data Index: 2053541 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1958. Min Range: -4.1958
Max Act: 4.0083. Min Act: -0.1700
Data Index: 8288024 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1958. Min Range: -4.1958
Max Act: 4.0083. Min Act: -0.1700
Data Index: 4066735 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.9770. Min Act: -0.1700
Data Index: 3236491 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.9770. Min Act: -0.1700
Data Index: 6140187 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.9457. Min Act: -0.1700
Data Index: 1516385 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.9145. Min Act: -0.1700
Data Index: 8723321 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.9145. Min Act: -0.1700
Data Index: 6229785 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.9145. Min Act: -0.1700
Data Index: 518504 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.9145. Min Act: -0.1700
Data Index: 3287847 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.8519. Min Act: -0.1700
Data Index: 1417204 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.8519. Min Act: -0.1700
Data Index: 8391047 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.8519. Min Act: -0.1700
Data Index: 2575630 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.8207. Min Act: -0.1700
Data Index: 80788 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.8207. Min Act: -0.1700
Data Index: 8535344 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.8207. Min Act: -0.1700
Data Index: 2063673 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1958. Min Range: -4.1958
Max Act: 3.8519. Min Act: -0.1700
Data Index: 7140938 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19