Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6224 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0351. Min Range: -5.0351
Max Act: 5.0351. Min Act: -0.1700
Data Index: 1829511 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.9414. Min Act: -0.1700
Data Index: 2914596 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8164. Min Act: -0.1700
Data Index: 2654396 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8164. Min Act: -0.1700
Data Index: 3633447 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8164. Min Act: -0.1700
Data Index: 2425130 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8164. Min Act: -0.1700
Data Index: 4713252 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8164. Min Act: -0.1700
Data Index: 7683116 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.8164. Min Act: -0.1700
Data Index: 900095 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7539. Min Act: -0.1700
Data Index: 2223305 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7539. Min Act: -0.1700
Data Index: 6502212 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7539. Min Act: -0.1700
Data Index: 6460102 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7539. Min Act: -0.1700
Data Index: 5426261 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7226. Min Act: -0.1700
Data Index: 7279038 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7226. Min Act: -0.1700
Data Index: 7731656 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7226. Min Act: -0.1700
Data Index: 7747188 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6914. Min Act: -0.1700
Data Index: 7076241 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6914. Min Act: -0.1700
Data Index: 538609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6601. Min Act: -0.1700
Data Index: 5349317 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.7226. Min Act: -0.1700
Data Index: 6723580 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0351. Min Range: -5.0351
Max Act: 4.6914. Min Act: -0.1700
Data Index: 197734 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19