Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 793 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3069. Min Range: -6.3069
Max Act: 6.3069. Min Act: -0.1700
Data Index: 8076799 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.9631. Min Act: -0.1700
Data Index: 3724191 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.9319. Min Act: -0.1700
Data Index: 5539548 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.9319. Min Act: -0.1700
Data Index: 5621476 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.8694. Min Act: -0.1700
Data Index: 2031108 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.8381. Min Act: -0.1700
Data Index: 1097724 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.7756. Min Act: -0.1700
Data Index: 667705 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.7756. Min Act: -0.1700
Data Index: 492871 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.7756. Min Act: -0.1700
Data Index: 7639276 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.7444. Min Act: -0.1700
Data Index: 1038998 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.7131. Min Act: -0.1700
Data Index: 8424946 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.7131. Min Act: -0.1700
Data Index: 3721816 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.7131. Min Act: -0.1700
Data Index: 4245792 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.7131. Min Act: -0.1700
Data Index: 7618518 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.7131. Min Act: -0.1700
Data Index: 3441897 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.6506. Min Act: -0.1700
Data Index: 4039368 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.6819. Min Act: -0.1700
Data Index: 5078427 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.6819. Min Act: -0.1700
Data Index: 5699750 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.6819. Min Act: -0.1700
Data Index: 1465627 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3069. Min Range: -6.3069
Max Act: 5.6506. Min Act: -0.1700
Data Index: 4611001 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19