Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0067. Min Range: -7.0067
Max Act: 7.0067. Min Act: -0.1700
Data Index: 6539724 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.8817. Min Act: -0.1700
Data Index: 6539721 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.7567. Min Act: -0.1700
Data Index: 6539723 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.7255. Min Act: -0.1700
Data Index: 6539728 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.6317. Min Act: -0.1700
Data Index: 6511776 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.6005. Min Act: -0.1700
Data Index: 6539722 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.6317. Min Act: -0.1700
Data Index: 6539729 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.4442. Min Act: -0.1700
Data Index: 4768217 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.4130. Min Act: -0.1700
Data Index: 6539725 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.3505. Min Act: -0.1700
Data Index: 6539727 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.3192. Min Act: -0.1700
Data Index: 5539268 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.3192. Min Act: -0.1700
Data Index: 7641243 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.3192. Min Act: -0.1700
Data Index: 7823772 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.3192. Min Act: -0.1700
Data Index: 2295506 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.2880. Min Act: -0.1700
Data Index: 8562302 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.3192. Min Act: -0.1700
Data Index: 8164018 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.2880. Min Act: -0.1700
Data Index: 6324252 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.2880. Min Act: -0.1700
Data Index: 7092076 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.2880. Min Act: -0.1700
Data Index: 5755141 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0067. Min Range: -7.0067
Max Act: 6.2880. Min Act: -0.1700
Data Index: 6539726 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19