Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.6713. Min Act: -0.1700
Data Index: 2941363 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.4525. Min Act: -0.1700
Data Index: 2981760 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.3588. Min Act: -0.1700
Data Index: 4024457 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.3275. Min Act: -0.1700
Data Index: 1568961 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2963. Min Act: -0.1700
Data Index: 5468680 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2963. Min Act: -0.1700
Data Index: 4473366 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2338. Min Act: -0.1700
Data Index: 5935499 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2650. Min Act: -0.1700
Data Index: 3730890 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2650. Min Act: -0.1700
Data Index: 2916994 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2338. Min Act: -0.1700
Data Index: 6379361 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2338. Min Act: -0.1700
Data Index: 6277433 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2025. Min Act: -0.1700
Data Index: 7636467 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2025. Min Act: -0.1700
Data Index: 1386162 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.2025. Min Act: -0.1700
Data Index: 3499129 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1713. Min Act: -0.1700
Data Index: 5755742 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1713. Min Act: -0.1700
Data Index: 5512547 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1713. Min Act: -0.1700
Data Index: 3663973 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1713. Min Act: -0.1700
Data Index: 710004 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1713. Min Act: -0.1700
Data Index: 6699753 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6713. Min Range: -6.6713
Max Act: 6.1400. Min Act: -0.1700
Data Index: 134489 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19