Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.9124. Min Act: -0.1700
Data Index: 3308213 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.8489. Min Act: -0.1700
Data Index: 5987507 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.8171. Min Act: -0.1700
Data Index: 3658661 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.8171. Min Act: -0.1700
Data Index: 4351965 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7693. Min Act: -0.1700
Data Index: 3689889 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7534. Min Act: -0.1700
Data Index: 4838681 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7534. Min Act: -0.1700
Data Index: 8427097 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7374. Min Act: -0.1700
Data Index: 1030167 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7374. Min Act: -0.1700
Data Index: 4076082 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7214. Min Act: -0.1700
Data Index: 5109369 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7374. Min Act: -0.1700
Data Index: 2386106 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7374. Min Act: -0.1700
Data Index: 7922881 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7374. Min Act: -0.1700
Data Index: 7063435 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7374. Min Act: -0.1700
Data Index: 2576210 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7054. Min Act: -0.1700
Data Index: 2882613 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7054. Min Act: -0.1700
Data Index: 5205646 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7214. Min Act: -0.1700
Data Index: 6681247 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7054. Min Act: -0.1700
Data Index: 2635026 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.7054. Min Act: -0.1700
Data Index: 4505064 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9124. Min Range: -2.9124
Max Act: 2.6734. Min Act: -0.1700
Data Index: 584847 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19