Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2294 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.7672. Min Act: -0.1700
Data Index: 4629761 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.5797. Min Act: -0.1700
Data Index: 2370782 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.3297. Min Act: -0.1700
Data Index: 5180459 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.2359. Min Act: -0.1700
Data Index: 982648 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.0484. Min Act: -0.1700
Data Index: 4019995 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.0484. Min Act: -0.1700
Data Index: 1683192 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.0172. Min Act: -0.1700
Data Index: 1468247 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.9859. Min Act: -0.1700
Data Index: 2577790 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.8922. Min Act: -0.1700
Data Index: 657740 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.8609. Min Act: -0.1700
Data Index: 6667907 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.8297. Min Act: -0.1700
Data Index: 2721781 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.8609. Min Act: -0.1700
Data Index: 7611538 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.8297. Min Act: -0.1700
Data Index: 1943400 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.8297. Min Act: -0.1700
Data Index: 8104950 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.8609. Min Act: -0.1700
Data Index: 8110654 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.7672. Min Act: -0.1700
Data Index: 353352 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.7672. Min Act: -0.1700
Data Index: 4449547 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.7359. Min Act: -0.1700
Data Index: 715433 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.7047. Min Act: -0.1700
Data Index: 4372790 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7672. Min Range: -6.7672
Max Act: 5.7359. Min Act: -0.1700
Data Index: 6499890 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19