Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2403 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1429. Min Range: -7.1429
Max Act: 7.1429. Min Act: -0.1700
Data Index: 6517088 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1429. Min Range: -7.1429
Max Act: 7.1429. Min Act: -0.1700
Data Index: 286360 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1429. Min Range: -7.1429
Max Act: 7.0179. Min Act: -0.1700
Data Index: 164124 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1429. Min Range: -7.1429
Max Act: 7.0179. Min Act: -0.1700
Data Index: 286359 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1429. Min Range: -7.1429
Max Act: 7.0179. Min Act: -0.1700
Data Index: 6153231 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.8929. Min Act: -0.1700
Data Index: 781636 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.8929. Min Act: -0.1699
Data Index: 7128193 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.8929. Min Act: -0.1700
Data Index: 6517082 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.8304. Min Act: -0.1700
Data Index: 781638 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.8304. Min Act: -0.1700
Data Index: 1851231 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.8304. Min Act: -0.1700
Data Index: 2433528 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.8304. Min Act: -0.1700
Data Index: 5662355 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.8304. Min Act: -0.1700
Data Index: 781632 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.7679. Min Act: -0.1700
Data Index: 5953456 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.7679. Min Act: -0.1700
Data Index: 5922198 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.7679. Min Act: -0.1700
Data Index: 525605 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.7054. Min Act: -0.1700
Data Index: 164116 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.7054. Min Act: -0.1700
Data Index: 6517084 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.7054. Min Act: -0.1700
Data Index: 4342143 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1429. Min Range: -7.1429
Max Act: 6.7054. Min Act: -0.1700
Data Index: 6517085 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19