Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3858 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.8324. Min Act: -0.1700
Data Index: 2655984 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.7699. Min Act: -0.1700
Data Index: 1570078 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.3949. Min Act: -0.1700
Data Index: 8399646 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.3324. Min Act: -0.1700
Data Index: 6579318 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.3012. Min Act: -0.1700
Data Index: 3363991 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.2699. Min Act: -0.1700
Data Index: 2444503 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.2699. Min Act: -0.1700
Data Index: 2447905 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.2074. Min Act: -0.1700
Data Index: 2897289 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.1762. Min Act: -0.1700
Data Index: 3134708 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.1762. Min Act: -0.1700
Data Index: 136536 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.1762. Min Act: -0.1700
Data Index: 2126503 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.1449. Min Act: -0.1700
Data Index: 4640001 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.1449. Min Act: -0.1700
Data Index: 4361433 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.1137. Min Act: -0.1700
Data Index: 6155697 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.0824. Min Act: -0.1700
Data Index: 4019419 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.0824. Min Act: -0.1700
Data Index: 2047231 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.1137. Min Act: -0.1700
Data Index: 7664778 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.0512. Min Act: -0.1700
Data Index: 932711 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.0512. Min Act: -0.1700
Data Index: 2824121 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8324. Min Range: -5.8324
Max Act: 5.0512. Min Act: -0.1700
Data Index: 5954502 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19