Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 11 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.8672. Min Act: -0.1700
Data Index: 1034045 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5234. Min Act: -0.1700
Data Index: 7903528 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.4609. Min Act: -0.1700
Data Index: 3682559 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.3984. Min Act: -0.1700
Data Index: 5458354 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.3359. Min Act: -0.1700
Data Index: 3069332 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2734. Min Act: -0.1700
Data Index: 4600671 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2734. Min Act: -0.1700
Data Index: 2823297 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2422. Min Act: -0.1700
Data Index: 6212415 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2422. Min Act: -0.1700
Data Index: 2371714 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2422. Min Act: -0.1700
Data Index: 4603201 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2422. Min Act: -0.1700
Data Index: 5458357 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2422. Min Act: -0.1700
Data Index: 141437 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2422. Min Act: -0.1700
Data Index: 7874102 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2109. Min Act: -0.1700
Data Index: 6515235 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2109. Min Act: -0.1700
Data Index: 3461125 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2109. Min Act: -0.1700
Data Index: 7335002 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.2109. Min Act: -0.1700
Data Index: 5651778 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.1797. Min Act: -0.1700
Data Index: 2159541 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.1797. Min Act: -0.1700
Data Index: 5708052 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.1484. Min Act: -0.1700
Data Index: 11293 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19