Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0007. Min Range: -9.0007
Max Act: 9.0007. Min Act: -0.1700
Data Index: 4405564 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0007. Min Range: -9.0007
Max Act: 8.0632. Min Act: -0.1700
Data Index: 4124886 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0007. Min Range: -9.0007
Max Act: 8.0320. Min Act: -0.1700
Data Index: 8110592 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0007. Min Range: -9.0007
Max Act: 8.0320. Min Act: -0.1700
Data Index: 5588780 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.9382. Min Act: -0.1700
Data Index: 6835145 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.5632. Min Act: -0.1700
Data Index: 3515069 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.5632. Min Act: -0.1700
Data Index: 4064081 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.5632. Min Act: -0.1700
Data Index: 166725 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.5007. Min Act: -0.1700
Data Index: 7396816 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.4382. Min Act: -0.1700
Data Index: 3892946 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.4382. Min Act: -0.1700
Data Index: 6575571 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.4070. Min Act: -0.1700
Data Index: 5156610 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.3132. Min Act: -0.1700
Data Index: 5056577 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.2820. Min Act: -0.1700
Data Index: 5631539 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.2195. Min Act: -0.1700
Data Index: 3181250 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.1882. Min Act: -0.1700
Data Index: 8581886 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.1570. Min Act: -0.1700
Data Index: 7757173 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.1570. Min Act: -0.1700
Data Index: 3873605 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.1882. Min Act: -0.1700
Data Index: 8321833 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0007. Min Range: -9.0007
Max Act: 7.1882. Min Act: -0.1700
Data Index: 5983873 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19