Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1882 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0131. Min Range: -6.0131
Max Act: 6.0131. Min Act: -0.1700
Data Index: 6570848 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.9506. Min Act: -0.1700
Data Index: 3590134 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.9819. Min Act: -0.1700
Data Index: 788280 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.9194. Min Act: -0.1700
Data Index: 6955222 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.8569. Min Act: -0.1700
Data Index: 6385800 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.8256. Min Act: -0.1700
Data Index: 485819 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7631. Min Act: -0.1700
Data Index: 3037262 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7944. Min Act: -0.1699
Data Index: 6955225 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7631. Min Act: -0.1700
Data Index: 3537465 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7631. Min Act: -0.1700
Data Index: 8087649 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7631. Min Act: -0.1700
Data Index: 598760 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7631. Min Act: -0.1700
Data Index: 1621485 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7319. Min Act: -0.1700
Data Index: 8298373 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7319. Min Act: -0.1700
Data Index: 1069052 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.6694. Min Act: -0.1700
Data Index: 1762731 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.6694. Min Act: -0.1700
Data Index: 1193502 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7006. Min Act: -0.1700
Data Index: 2356943 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.7006. Min Act: -0.1700
Data Index: 5320371 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.6694. Min Act: -0.1700
Data Index: 915404 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0131. Min Range: -6.0131
Max Act: 5.6381. Min Act: -0.1700
Data Index: 4585287 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19