Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6208 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.9821. Min Act: -0.1700
Data Index: 192978 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.9821. Min Act: -0.1700
Data Index: 3002301 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.9509. Min Act: -0.1700
Data Index: 1479140 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.9509. Min Act: -0.1700
Data Index: 6536594 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.9821. Min Act: -0.1700
Data Index: 664704 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.8884. Min Act: -0.1700
Data Index: 7183473 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.8884. Min Act: -0.1700
Data Index: 1856450 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.8571. Min Act: -0.1700
Data Index: 3326308 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.8259. Min Act: -0.1700
Data Index: 4687083 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.8259. Min Act: -0.1700
Data Index: 5785025 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7946. Min Act: -0.1700
Data Index: 511726 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7634. Min Act: -0.1700
Data Index: 4142014 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7009. Min Act: -0.1700
Data Index: 7306538 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7321. Min Act: -0.1700
Data Index: 5311039 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7009. Min Act: -0.1700
Data Index: 5816426 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7009. Min Act: -0.1700
Data Index: 7842539 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7009. Min Act: -0.1700
Data Index: 5196315 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7009. Min Act: -0.1700
Data Index: 7139704 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7009. Min Act: -0.1700
Data Index: 310021 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9821. Min Range: -5.9821
Max Act: 5.7009. Min Act: -0.1700
Data Index: 8085708 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19