Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.2212. Min Act: -0.1700
Data Index: 5202991 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.1274. Min Act: -0.1700
Data Index: 7731436 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.1274. Min Act: -0.1700
Data Index: 1912857 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9712. Min Act: -0.1700
Data Index: 5981428 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.0024. Min Act: -0.1700
Data Index: 5931173 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9712. Min Act: -0.1700
Data Index: 8177431 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9712. Min Act: -0.1700
Data Index: 6133870 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9399. Min Act: -0.1700
Data Index: 8523257 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9399. Min Act: -0.1700
Data Index: 447068 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9399. Min Act: -0.1700
Data Index: 6930700 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9712. Min Act: -0.1700
Data Index: 1829692 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9399. Min Act: -0.1700
Data Index: 7855660 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9087. Min Act: -0.1700
Data Index: 4468638 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9087. Min Act: -0.1700
Data Index: 153076 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8774. Min Act: -0.1700
Data Index: 3914853 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8774. Min Act: -0.1700
Data Index: 5325476 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8774. Min Act: -0.1700
Data Index: 1928844 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9087. Min Act: -0.1700
Data Index: 748306 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8462. Min Act: -0.1700
Data Index: 2198348 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8774. Min Act: -0.1700
Data Index: 8006359 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19