Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4898 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1795. Min Range: -5.1795
Max Act: 5.1795. Min Act: -0.1700
Data Index: 8713919 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.9920. Min Act: -0.1700
Data Index: 386470 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.9295. Min Act: -0.1700
Data Index: 1403417 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.8670. Min Act: -0.1700
Data Index: 1092387 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.8045. Min Act: -0.1700
Data Index: 1233021 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.8045. Min Act: -0.1700
Data Index: 8721064 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7420. Min Act: -0.1700
Data Index: 7162172 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7420. Min Act: -0.1700
Data Index: 1028224 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7732. Min Act: -0.1700
Data Index: 6932497 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7732. Min Act: -0.1700
Data Index: 5372246 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7420. Min Act: -0.1700
Data Index: 6464573 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7107. Min Act: -0.1700
Data Index: 5317552 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.6795. Min Act: -0.1700
Data Index: 477694 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7107. Min Act: -0.1700
Data Index: 7982587 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7107. Min Act: -0.1700
Data Index: 1257845 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2827406 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7107. Min Act: -0.1700
Data Index: 3622614 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7107. Min Act: -0.1700
Data Index: 891170 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.7107. Min Act: -0.1700
Data Index: 4422902 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1795. Min Range: -5.1795
Max Act: 4.6795. Min Act: -0.1700
Data Index: 4039802 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19