Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3934 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.7330. Min Act: -0.1700
Data Index: 7471732 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5922. Min Act: -0.1700
Data Index: 8281511 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5765. Min Act: -0.1700
Data Index: 55505 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5765. Min Act: -0.1700
Data Index: 349262 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5452. Min Act: -0.1700
Data Index: 1099418 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5295. Min Act: -0.1700
Data Index: 3596422 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5139. Min Act: -0.1700
Data Index: 961785 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5139. Min Act: -0.1700
Data Index: 2281841 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4982. Min Act: -0.1700
Data Index: 359828 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4512. Min Act: -0.1700
Data Index: 8228615 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4669. Min Act: -0.1700
Data Index: 8260718 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4355. Min Act: -0.1700
Data Index: 6615882 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4355. Min Act: -0.1700
Data Index: 7560008 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4199. Min Act: -0.1700
Data Index: 2696665 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4042. Min Act: -0.1700
Data Index: 6381286 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.3885. Min Act: -0.1700
Data Index: 8474699 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.3885. Min Act: -0.1700
Data Index: 4740105 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4042. Min Act: -0.1700
Data Index: 8642750 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.3885. Min Act: -0.1700
Data Index: 8606035 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.3885. Min Act: -0.1700
Data Index: 921273 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19