Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4657 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.6011. Min Act: -0.1700
Data Index: 1415611 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.5698. Min Act: -0.1700
Data Index: 4138413 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4448. Min Act: -0.1700
Data Index: 5568229 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4761. Min Act: -0.1700
Data Index: 7274948 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4448. Min Act: -0.1700
Data Index: 1627938 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4448. Min Act: -0.1700
Data Index: 6087012 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4448. Min Act: -0.1700
Data Index: 1336001 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4448. Min Act: -0.1700
Data Index: 668512 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4136. Min Act: -0.1700
Data Index: 6009141 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4136. Min Act: -0.1700
Data Index: 1887797 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4136. Min Act: -0.1700
Data Index: 6886880 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4136. Min Act: -0.1700
Data Index: 2724446 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3823. Min Act: -0.1700
Data Index: 4414673 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3823. Min Act: -0.1700
Data Index: 1902625 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3823. Min Act: -0.1700
Data Index: 2642102 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3823. Min Act: -0.1700
Data Index: 369820 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3510. Min Act: -0.1700
Data Index: 6009138 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3510. Min Act: -0.1700
Data Index: 1176020 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3823. Min Act: -0.1700
Data Index: 1171177 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3510. Min Act: -0.1700
Data Index: 4224517 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19