Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.9682. Min Act: -0.1700
Data Index: 7199195 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.8432. Min Act: -0.1700
Data Index: 3934631 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.8432. Min Act: -0.1700
Data Index: 2757625 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.7494. Min Act: -0.1700
Data Index: 714067 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.7182. Min Act: -0.1700
Data Index: 6091247 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.6869. Min Act: -0.1700
Data Index: 1813520 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.6244. Min Act: -0.1700
Data Index: 4876493 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.6244. Min Act: -0.1700
Data Index: 7821353 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.5932. Min Act: -0.1700
Data Index: 6908975 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.6244. Min Act: -0.1700
Data Index: 5263344 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.5932. Min Act: -0.1700
Data Index: 4818952 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.5619. Min Act: -0.1700
Data Index: 1955028 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.5619. Min Act: -0.1700
Data Index: 1122362 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.5307. Min Act: -0.1700
Data Index: 5500117 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.5619. Min Act: -0.1700
Data Index: 7281127 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.4994. Min Act: -0.1700
Data Index: 2643819 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.5307. Min Act: -0.1700
Data Index: 2682974 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.5307. Min Act: -0.1700
Data Index: 681629 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.4994. Min Act: -0.1700
Data Index: 4732383 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9682. Min Range: -4.9682
Max Act: 4.4994. Min Act: -0.1700
Data Index: 5352390 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19