Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 574 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.9939. Min Act: -0.1700
Data Index: 4091202 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0564. Min Range: -8.0564
Max Act: 8.0564. Min Act: -0.1700
Data Index: 5032331 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.8064. Min Act: -0.1700
Data Index: 7460994 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.7439. Min Act: -0.1700
Data Index: 1108726 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.6814. Min Act: -0.1700
Data Index: 4091211 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.6814. Min Act: -0.1700
Data Index: 5259710 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.5564. Min Act: -0.1700
Data Index: 465150 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.5564. Min Act: -0.1700
Data Index: 4091214 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.4939. Min Act: -0.1700
Data Index: 4091201 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.4314. Min Act: -0.1700
Data Index: 4091210 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.4314. Min Act: -0.1700
Data Index: 4312307 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.3064. Min Act: -0.1700
Data Index: 6546599 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.3064. Min Act: -0.1700
Data Index: 7065558 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.3064. Min Act: -0.1700
Data Index: 3562226 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.3064. Min Act: -0.1700
Data Index: 7460992 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.2439. Min Act: -0.1700
Data Index: 985478 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.2126. Min Act: -0.1700
Data Index: 8615367 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.2126. Min Act: -0.1700
Data Index: 5145117 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.2126. Min Act: -0.1700
Data Index: 1501541 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0564. Min Range: -8.0564
Max Act: 7.2126. Min Act: -0.1700
Data Index: 728835 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19