Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.9410. Min Act: -0.1700
Data Index: 1090850 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.9069. Min Act: -0.1700
Data Index: 1399972 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8899. Min Act: -0.1700
Data Index: 5685445 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8899. Min Act: -0.1700
Data Index: 6436669 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8557. Min Act: -0.1700
Data Index: 1730586 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8557. Min Act: -0.1700
Data Index: 8617382 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8728. Min Act: -0.1700
Data Index: 469486 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8385. Min Act: -0.1700
Data Index: 7674153 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8385. Min Act: -0.1698
Data Index: 1090849 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8385. Min Act: -0.1700
Data Index: 7733502 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8385. Min Act: -0.1700
Data Index: 7679440 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8385. Min Act: -0.1700
Data Index: 2341028 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8385. Min Act: -0.1700
Data Index: 3617920 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8385. Min Act: -0.1700
Data Index: 4772026 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8214. Min Act: -0.1700
Data Index: 6373922 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8042. Min Act: -0.1700
Data Index: 5791555 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8214. Min Act: -0.1700
Data Index: 1239629 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8214. Min Act: -0.1700
Data Index: 7679438 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8214. Min Act: -0.1700
Data Index: 3778220 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9410. Min Range: -1.9410
Max Act: 1.8214. Min Act: -0.1700
Data Index: 258574 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19