Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 843 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2205. Min Range: -4.2205
Max Act: 4.2205. Min Act: -0.1700
Data Index: 6248969 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2205. Min Range: -4.2205
Max Act: 4.1268. Min Act: -0.1700
Data Index: 350271 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2205. Min Range: -4.2205
Max Act: 4.1893. Min Act: -0.1700
Data Index: 782467 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2205. Min Range: -4.2205
Max Act: 4.0643. Min Act: -0.1700
Data Index: 6698350 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2205. Min Range: -4.2205
Max Act: 4.0643. Min Act: -0.1700
Data Index: 3177244 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9705. Min Act: -0.1700
Data Index: 7147595 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2205. Min Range: -4.2205
Max Act: 4.0018. Min Act: -0.1700
Data Index: 7870506 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2205. Min Range: -4.2205
Max Act: 4.0018. Min Act: -0.1700
Data Index: 4496032 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9705. Min Act: -0.1700
Data Index: 3587293 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9392. Min Act: -0.1700
Data Index: 1974258 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9392. Min Act: -0.1700
Data Index: 3995787 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9392. Min Act: -0.1700
Data Index: 3822982 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9392. Min Act: -0.1700
Data Index: 680289 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9080. Min Act: -0.1700
Data Index: 7203495 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9080. Min Act: -0.1700
Data Index: 4960524 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9080. Min Act: -0.1700
Data Index: 288829 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.9080. Min Act: -0.1700
Data Index: 3446945 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.8767. Min Act: -0.1700
Data Index: 288831 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.8454. Min Act: -0.1700
Data Index: 3824884 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2205. Min Range: -4.2205
Max Act: 3.8767. Min Act: -0.1700
Data Index: 3222463 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19