Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.2453. Min Act: -0.1700
Data Index: 3082185 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.2140. Min Act: -0.1700
Data Index: 6055240 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1515. Min Act: -0.1700
Data Index: 8399404 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1515. Min Act: -0.1700
Data Index: 7138489 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1827. Min Act: -0.1700
Data Index: 707591 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.1202. Min Act: -0.1700
Data Index: 762472 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0890. Min Act: -0.1700
Data Index: 7633837 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0890. Min Act: -0.1700
Data Index: 5131996 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0890. Min Act: -0.1700
Data Index: 1704769 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 5723231 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0577. Min Act: -0.1700
Data Index: 5069530 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0577. Min Act: -0.1700
Data Index: 364446 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 4923304 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 6751847 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 5351619 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2453. Min Range: -4.2453
Max Act: 3.9952. Min Act: -0.1700
Data Index: 5236819 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 4410079 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 4300680 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 2689419 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2453. Min Range: -4.2453
Max Act: 4.0265. Min Act: -0.1700
Data Index: 7354433 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19