Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1557 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3542. Min Range: -8.3542
Max Act: 8.3542. Min Act: -0.1700
Data Index: 8052204 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3542. Min Range: -8.3542
Max Act: 8.2917. Min Act: -0.1700
Data Index: 2708368 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3542. Min Range: -8.3542
Max Act: 8.2292. Min Act: -0.1700
Data Index: 6618236 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3542. Min Range: -8.3542
Max Act: 8.1042. Min Act: -0.1700
Data Index: 3675579 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3542. Min Range: -8.3542
Max Act: 8.1042. Min Act: -0.1700
Data Index: 2425835 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.9167. Min Act: -0.1700
Data Index: 4398079 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.9167. Min Act: -0.1700
Data Index: 2155204 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.9792. Min Act: -0.1700
Data Index: 2161638 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.9792. Min Act: -0.1700
Data Index: 1700757 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.9167. Min Act: -0.1700
Data Index: 8631312 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.8542. Min Act: -0.1700
Data Index: 3293060 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.8542. Min Act: -0.1700
Data Index: 481796 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.7917. Min Act: -0.1700
Data Index: 6511431 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.8542. Min Act: -0.1700
Data Index: 1314040 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.8542. Min Act: -0.1700
Data Index: 5022750 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.7604. Min Act: -0.1700
Data Index: 7206974 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.7917. Min Act: -0.1700
Data Index: 8830105 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.8542. Min Act: -0.1700
Data Index: 7046758 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.7917. Min Act: -0.1700
Data Index: 4687890 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3542. Min Range: -8.3542
Max Act: 7.7604. Min Act: -0.1700
Data Index: 7795164 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19