Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5463 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.6226. Min Act: -0.1700
Data Index: 4169144 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.6226. Min Act: -0.1700
Data Index: 4925554 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.5601. Min Act: -0.1700
Data Index: 3289609 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.4664. Min Act: -0.1700
Data Index: 520457 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.4351. Min Act: -0.1700
Data Index: 1750591 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2476. Min Act: -0.1700
Data Index: 4528305 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2476. Min Act: -0.1700
Data Index: 8487511 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2164. Min Act: -0.1700
Data Index: 2965852 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2164. Min Act: -0.1700
Data Index: 1893561 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1851. Min Act: -0.1700
Data Index: 6028721 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1851. Min Act: -0.1700
Data Index: 8063353 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1851. Min Act: -0.1700
Data Index: 307485 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1851. Min Act: -0.1700
Data Index: 5128662 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1539. Min Act: -0.1700
Data Index: 6215832 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1851. Min Act: -0.1700
Data Index: 6509420 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1226. Min Act: -0.1700
Data Index: 4597156 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1226. Min Act: -0.1700
Data Index: 771422 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1226. Min Act: -0.1700
Data Index: 3160136 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1539. Min Act: -0.1700
Data Index: 4336921 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1226. Min Act: -0.1700
Data Index: 7723566 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19