Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4386 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.6560. Min Act: -0.1700
Data Index: 1790505 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.5308. Min Act: -0.1700
Data Index: 551705 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.3741. Min Act: -0.1700
Data Index: 1092387 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.3427. Min Act: -0.1700
Data Index: 2191366 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.3113. Min Act: -0.1700
Data Index: 6521008 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.3427. Min Act: -0.1700
Data Index: 1938721 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.3427. Min Act: -0.1700
Data Index: 3030837 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.3270. Min Act: -0.1700
Data Index: 4721811 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2956. Min Act: -0.1700
Data Index: 634552 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.3113. Min Act: -0.1700
Data Index: 6988492 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2799. Min Act: -0.1700
Data Index: 4921663 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2956. Min Act: -0.1700
Data Index: 2562977 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2956. Min Act: -0.1700
Data Index: 2424336 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2799. Min Act: -0.1700
Data Index: 8578628 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2956. Min Act: -0.1700
Data Index: 404237 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2799. Min Act: -0.1700
Data Index: 3176656 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2799. Min Act: -0.1700
Data Index: 8269964 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2485. Min Act: -0.1700
Data Index: 5108123 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2485. Min Act: -0.1700
Data Index: 3903568 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6560. Min Range: -3.6560
Max Act: 3.2328. Min Act: -0.1700
Data Index: 3723364 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19