Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4908 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.9493. Min Act: -0.1700
Data Index: 4050825 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.9493. Min Act: -0.1700
Data Index: 4584521 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.8868. Min Act: -0.1700
Data Index: 6787352 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.7618. Min Act: -0.1700
Data Index: 7202037 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.6368. Min Act: -0.1700
Data Index: 4399670 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.5743. Min Act: -0.1700
Data Index: 5555619 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.5743. Min Act: -0.1700
Data Index: 8093244 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.5743. Min Act: -0.1700
Data Index: 4338285 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.5118. Min Act: -0.1700
Data Index: 2453875 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.5118. Min Act: -0.1700
Data Index: 1253914 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.5118. Min Act: -0.1700
Data Index: 6522005 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.5118. Min Act: -0.1700
Data Index: 1126254 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.5118. Min Act: -0.1700
Data Index: 6026826 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.4493. Min Act: -0.1700
Data Index: 6300442 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.4180. Min Act: -0.1700
Data Index: 3711424 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.4180. Min Act: -0.1700
Data Index: 3151506 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.3868. Min Act: -0.1700
Data Index: 2458169 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.4180. Min Act: -0.1700
Data Index: 5199077 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.3555. Min Act: -0.1700
Data Index: 3519883 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9493. Min Range: -7.9493
Max Act: 7.3555. Min Act: -0.1700
Data Index: 5317526 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19