Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4523 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.5834. Min Act: -0.1700
Data Index: 6508223 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.4897. Min Act: -0.1700
Data Index: 305926 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.3022. Min Act: -0.1700
Data Index: 736935 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.2709. Min Act: -0.1700
Data Index: 5662803 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.2397. Min Act: -0.1700
Data Index: 2105572 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.2397. Min Act: -0.1700
Data Index: 3880343 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.1772. Min Act: -0.1700
Data Index: 35520 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.2084. Min Act: -0.1700
Data Index: 1025201 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.2084. Min Act: -0.1700
Data Index: 8522463 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.1772. Min Act: -0.1700
Data Index: 4372286 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.1772. Min Act: -0.1700
Data Index: 8081278 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.1147. Min Act: -0.1700
Data Index: 158705 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.1459. Min Act: -0.1700
Data Index: 1350548 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.1147. Min Act: -0.1700
Data Index: 905587 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.0834. Min Act: -0.1700
Data Index: 6560973 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5834. Min Range: -6.5834
Max Act: 6.0522. Min Act: -0.1700
Data Index: 5732871 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5834. Min Range: -6.5834
Max Act: 5.9897. Min Act: -0.1700
Data Index: 6361976 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5834. Min Range: -6.5834
Max Act: 5.9897. Min Act: -0.1700
Data Index: 8168994 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5834. Min Range: -6.5834
Max Act: 5.9897. Min Act: -0.1700
Data Index: 2347569 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5834. Min Range: -6.5834
Max Act: 5.9897. Min Act: -0.1700
Data Index: 8266385 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19