Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5038 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7677. Min Act: -0.1700
Data Index: 3018148 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.7365. Min Act: -0.1700
Data Index: 4114147 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6740. Min Act: -0.1700
Data Index: 2895096 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6115. Min Act: -0.1700
Data Index: 726522 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6115. Min Act: -0.1700
Data Index: 8497633 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.6115. Min Act: -0.1700
Data Index: 4502219 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5802. Min Act: -0.1700
Data Index: 2478675 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5802. Min Act: -0.1700
Data Index: 5365898 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5802. Min Act: -0.1700
Data Index: 6168274 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5802. Min Act: -0.1700
Data Index: 1869376 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5490. Min Act: -0.1700
Data Index: 6895974 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5490. Min Act: -0.1700
Data Index: 2291066 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5490. Min Act: -0.1700
Data Index: 7127518 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5490. Min Act: -0.1700
Data Index: 7389683 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5490. Min Act: -0.1700
Data Index: 8229207 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5490. Min Act: -0.1700
Data Index: 3763508 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5177. Min Act: -0.1700
Data Index: 1551713 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5177. Min Act: -0.1700
Data Index: 2620221 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5490. Min Act: -0.1700
Data Index: 2257629 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7677. Min Range: -4.7677
Max Act: 4.5177. Min Act: -0.1700
Data Index: 5026939 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19