Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.6963. Min Act: -0.1700
Data Index: 1735152 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.6026. Min Act: -0.1700
Data Index: 5031710 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.2588. Min Act: -0.1700
Data Index: 969812 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.2588. Min Act: -0.1700
Data Index: 7996171 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.1963. Min Act: -0.1700
Data Index: 7112189 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.1963. Min Act: -0.1700
Data Index: 8058915 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.1026. Min Act: -0.1700
Data Index: 7770434 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.0713. Min Act: -0.1700
Data Index: 3622968 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.0713. Min Act: -0.1700
Data Index: 5496050 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.0401. Min Act: -0.1700
Data Index: 35905 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6963. Min Range: -6.6963
Max Act: 5.9776. Min Act: -0.1700
Data Index: 348843 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.0088. Min Act: -0.1700
Data Index: 650818 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.0401. Min Act: -0.1700
Data Index: 5510886 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.0088. Min Act: -0.1700
Data Index: 7818923 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6963. Min Range: -6.6963
Max Act: 6.0088. Min Act: -0.1700
Data Index: 7507626 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6963. Min Range: -6.6963
Max Act: 5.9776. Min Act: -0.1700
Data Index: 4099136 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6963. Min Range: -6.6963
Max Act: 5.9463. Min Act: -0.1700
Data Index: 1696018 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6963. Min Range: -6.6963
Max Act: 5.9463. Min Act: -0.1700
Data Index: 3588314 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6963. Min Range: -6.6963
Max Act: 5.8838. Min Act: -0.1700
Data Index: 421845 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6963. Min Range: -6.6963
Max Act: 5.8838. Min Act: -0.1700
Data Index: 7086698 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19