Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2144 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.7703. Min Act: -0.1700
Data Index: 4681043 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.6608. Min Act: -0.1700
Data Index: 711305 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.5669. Min Act: -0.1700
Data Index: 1322247 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.5669. Min Act: -0.1700
Data Index: 8428020 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.5356. Min Act: -0.1700
Data Index: 37566 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.5356. Min Act: -0.1700
Data Index: 4779648 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.5043. Min Act: -0.1700
Data Index: 3643755 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4886. Min Act: -0.1700
Data Index: 1989532 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4730. Min Act: -0.1700
Data Index: 4211176 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.5043. Min Act: -0.1700
Data Index: 332268 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4730. Min Act: -0.1700
Data Index: 1866225 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4573. Min Act: -0.1700
Data Index: 7856523 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4886. Min Act: -0.1700
Data Index: 5422762 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4730. Min Act: -0.1700
Data Index: 7543810 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4573. Min Act: -0.1700
Data Index: 1283859 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4573. Min Act: -0.1700
Data Index: 223957 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4260. Min Act: -0.1700
Data Index: 4876670 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4416. Min Act: -0.1700
Data Index: 8062741 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4260. Min Act: -0.1700
Data Index: 1005878 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7703. Min Range: -3.7703
Max Act: 3.4416. Min Act: -0.1700
Data Index: 8591727 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19