Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0269. Min Range: -8.0269
Max Act: 8.0269. Min Act: -0.1700
Data Index: 3746483 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.8394. Min Act: -0.1700
Data Index: 1007652 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.7769. Min Act: -0.1700
Data Index: 737950 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.7144. Min Act: -0.1700
Data Index: 835429 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.7144. Min Act: -0.1700
Data Index: 7373070 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.5894. Min Act: -0.1700
Data Index: 2098101 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.6519. Min Act: -0.1700
Data Index: 3348762 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.5269. Min Act: -0.1700
Data Index: 6196928 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.5581. Min Act: -0.1700
Data Index: 3770655 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.5581. Min Act: -0.1700
Data Index: 428847 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.5581. Min Act: -0.1700
Data Index: 8463552 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.4956. Min Act: -0.1700
Data Index: 1729194 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.4644. Min Act: -0.1700
Data Index: 6325717 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.4644. Min Act: -0.1700
Data Index: 856240 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.4019. Min Act: -0.1700
Data Index: 5335294 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.4019. Min Act: -0.1700
Data Index: 5371794 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.4019. Min Act: -0.1700
Data Index: 387926 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.4331. Min Act: -0.1700
Data Index: 4532356 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.3394. Min Act: -0.1700
Data Index: 5705750 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0269. Min Range: -8.0269
Max Act: 7.3706. Min Act: -0.1700
Data Index: 3435127 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19