Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4127 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0569. Min Range: -5.0569
Max Act: 5.0569. Min Act: -0.1700
Data Index: 3398972 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0569. Min Range: -5.0569
Max Act: 5.0569. Min Act: -0.1700
Data Index: 3733834 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9631. Min Act: -0.1700
Data Index: 2139686 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9631. Min Act: -0.1700
Data Index: 2677966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9631. Min Act: -0.1700
Data Index: 2535062 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9006. Min Act: -0.1700
Data Index: 1791817 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9319. Min Act: -0.1700
Data Index: 2584015 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9319. Min Act: -0.1700
Data Index: 6522260 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.8694. Min Act: -0.1700
Data Index: 2210614 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9006. Min Act: -0.1700
Data Index: 6347785 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9006. Min Act: -0.1700
Data Index: 7885061 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9006. Min Act: -0.1700
Data Index: 5082669 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9006. Min Act: -0.1700
Data Index: 4833441 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9319. Min Act: -0.1700
Data Index: 6297576 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9006. Min Act: -0.1700
Data Index: 4793765 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9006. Min Act: -0.1700
Data Index: 7499576 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.9006. Min Act: -0.1700
Data Index: 1467565 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.8694. Min Act: -0.1700
Data Index: 933237 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.8694. Min Act: -0.1700
Data Index: 5676791 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0569. Min Range: -5.0569
Max Act: 4.8694. Min Act: -0.1700
Data Index: 2738886 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19