Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.8198. Min Act: -0.1700
Data Index: 2574108 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.7885. Min Act: -0.1700
Data Index: 8787582 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.6948. Min Act: -0.1700
Data Index: 1259034 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.7260. Min Act: -0.1700
Data Index: 2841569 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.6323. Min Act: -0.1700
Data Index: 295111 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.6010. Min Act: -0.1700
Data Index: 5281485 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5697. Min Act: -0.1700
Data Index: 239154 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.6010. Min Act: -0.1700
Data Index: 7784123 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5697. Min Act: -0.1700
Data Index: 7153025 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5697. Min Act: -0.1700
Data Index: 6034350 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5385. Min Act: -0.1700
Data Index: 1853646 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5385. Min Act: -0.1700
Data Index: 7771588 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5072. Min Act: -0.1700
Data Index: 6410016 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5072. Min Act: -0.1700
Data Index: 5317531 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5072. Min Act: -0.1700
Data Index: 6586213 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5072. Min Act: -0.1700
Data Index: 884437 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5072. Min Act: -0.1700
Data Index: 5873396 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.5072. Min Act: -0.1700
Data Index: 8308972 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.4760. Min Act: -0.1700
Data Index: 1168249 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8198. Min Range: -4.8198
Max Act: 4.4760. Min Act: -0.1700
Data Index: 7560439 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19