Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1392 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4273. Min Range: -4.4273
Max Act: 4.4273. Min Act: -0.1700
Data Index: 3631612 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4273. Min Range: -4.4273
Max Act: 4.0835. Min Act: -0.1700
Data Index: 1792426 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.8647. Min Act: -0.1700
Data Index: 8491932 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.8334. Min Act: -0.1700
Data Index: 2348556 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.8334. Min Act: -0.1700
Data Index: 4002680 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.8334. Min Act: -0.1700
Data Index: 4939243 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.8022. Min Act: -0.1700
Data Index: 4619194 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.7709. Min Act: -0.1700
Data Index: 3199972 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.7709. Min Act: -0.1700
Data Index: 3689599 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.7396. Min Act: -0.1700
Data Index: 7657371 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.7396. Min Act: -0.1700
Data Index: 609915 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.7396. Min Act: -0.1700
Data Index: 3445802 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.7083. Min Act: -0.1700
Data Index: 2219550 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.7083. Min Act: -0.1700
Data Index: 6813453 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.6927. Min Act: -0.1700
Data Index: 5374183 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.7083. Min Act: -0.1700
Data Index: 7378207 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.6770. Min Act: -0.1700
Data Index: 4518040 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.6927. Min Act: -0.1700
Data Index: 3227644 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.6614. Min Act: -0.1700
Data Index: 3786808 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4273. Min Range: -4.4273
Max Act: 3.6458. Min Act: -0.1700
Data Index: 1172709 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19