Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2388 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.7920. Min Act: -0.1700
Data Index: 2058624 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.3545. Min Act: -0.1700
Data Index: 7219546 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.2295. Min Act: -0.1700
Data Index: 3969963 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.2295. Min Act: -0.1700
Data Index: 4924868 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.1670. Min Act: -0.1700
Data Index: 2349817 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.1670. Min Act: -0.1700
Data Index: 7284806 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.1983. Min Act: -0.1700
Data Index: 206665 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.1358. Min Act: -0.1700
Data Index: 1343020 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.1045. Min Act: -0.1700
Data Index: 7982789 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.1358. Min Act: -0.1700
Data Index: 5129245 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.1358. Min Act: -0.1700
Data Index: 114322 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.1045. Min Act: -0.1700
Data Index: 1231600 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.0733. Min Act: -0.1700
Data Index: 6824818 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.0733. Min Act: -0.1700
Data Index: 7899673 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.0420. Min Act: -0.1700
Data Index: 2956640 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.0420. Min Act: -0.1700
Data Index: 3883108 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.0108. Min Act: -0.1700
Data Index: 79443 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7920. Min Range: -6.7920
Max Act: 5.9795. Min Act: -0.1700
Data Index: 6933500 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.0108. Min Act: -0.1700
Data Index: 4365355 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7920. Min Range: -6.7920
Max Act: 6.0108. Min Act: -0.1700
Data Index: 501538 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19