Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3527 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.8632. Min Act: -0.1700
Data Index: 6281703 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.8007. Min Act: -0.1700
Data Index: 5898506 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.8007. Min Act: -0.1700
Data Index: 261367 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.7069. Min Act: -0.1700
Data Index: 4568660 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.5194. Min Act: -0.1700
Data Index: 8561280 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.4882. Min Act: -0.1700
Data Index: 470159 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.4882. Min Act: -0.1700
Data Index: 7265097 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.4569. Min Act: -0.1700
Data Index: 1048928 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.4569. Min Act: -0.1700
Data Index: 2935522 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.4569. Min Act: -0.1700
Data Index: 4641221 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.4569. Min Act: -0.1700
Data Index: 4736028 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.4569. Min Act: -0.1700
Data Index: 2746396 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.4257. Min Act: -0.1700
Data Index: 2440212 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.3632. Min Act: -0.1700
Data Index: 5930350 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.3319. Min Act: -0.1700
Data Index: 4965736 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.3632. Min Act: -0.1700
Data Index: 3905512 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.3319. Min Act: -0.1700
Data Index: 6301511 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.3007. Min Act: -0.1700
Data Index: 3765271 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.3007. Min Act: -0.1700
Data Index: 4421951 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8632. Min Range: -6.8632
Max Act: 6.3007. Min Act: -0.1700
Data Index: 5677495 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19