Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.4429. Min Act: -0.1700
Data Index: 524324 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.3491. Min Act: -0.1700
Data Index: 614185 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.2241. Min Act: -0.1700
Data Index: 4937278 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.1929. Min Act: -0.1700
Data Index: 4621174 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.1304. Min Act: -0.1700
Data Index: 7728941 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.1304. Min Act: -0.1691
Data Index: 4621176 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0991. Min Act: -0.1700
Data Index: 1310007 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0679. Min Act: -0.1700
Data Index: 8639735 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0679. Min Act: -0.1700
Data Index: 3620654 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0679. Min Act: -0.1700
Data Index: 5329514 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0679. Min Act: -0.1700
Data Index: 5983415 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0679. Min Act: -0.1700
Data Index: 1873180 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0679. Min Act: -0.1700
Data Index: 91470 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0366. Min Act: -0.1700
Data Index: 6939935 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0366. Min Act: -0.1700
Data Index: 2109475 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0366. Min Act: -0.1700
Data Index: 7193762 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0054. Min Act: -0.1700
Data Index: 8246256 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0366. Min Act: -0.1700
Data Index: 2076461 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0366. Min Act: -0.1700
Data Index: 7869475 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4429. Min Range: -5.4429
Max Act: 5.0054. Min Act: -0.1700
Data Index: 5396100 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19