Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1404 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.9243. Min Act: -0.1700
Data Index: 2908259 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.8767. Min Act: -0.1700
Data Index: 6593986 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.8131. Min Act: -0.1700
Data Index: 6491157 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.8131. Min Act: -0.1700
Data Index: 489838 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7972. Min Act: -0.1700
Data Index: 6388854 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7972. Min Act: -0.1700
Data Index: 4393462 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7972. Min Act: -0.1700
Data Index: 5701209 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7494. Min Act: -0.1700
Data Index: 5716971 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7494. Min Act: -0.1700
Data Index: 2817047 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7334. Min Act: -0.1700
Data Index: 4238765 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7334. Min Act: -0.1700
Data Index: 6009601 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7174. Min Act: -0.1700
Data Index: 257616 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7174. Min Act: -0.1700
Data Index: 5435208 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7014. Min Act: -0.1700
Data Index: 2744164 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7174. Min Act: -0.1700
Data Index: 5894041 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.6854. Min Act: -0.1700
Data Index: 8364451 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.7014. Min Act: -0.1700
Data Index: 5725376 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.6854. Min Act: -0.1700
Data Index: 32413 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.6854. Min Act: -0.1700
Data Index: 1244576 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9243. Min Range: -2.9243
Max Act: 2.6854. Min Act: -0.1700
Data Index: 5752837 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19