Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1015 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1621. Min Range: -9.1621
Max Act: 9.1621. Min Act: -0.1700
Data Index: 7968733 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.5371. Min Act: -0.1700
Data Index: 6522062 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.4121. Min Act: -0.1700
Data Index: 6547106 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.4121. Min Act: -0.1700
Data Index: 5976047 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.2871. Min Act: -0.1700
Data Index: 8660401 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.2871. Min Act: -0.1700
Data Index: 5279166 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.2871. Min Act: -0.1700
Data Index: 1423180 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.2246. Min Act: -0.1700
Data Index: 8627550 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.1621. Min Act: -0.1700
Data Index: 8372078 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.1621. Min Act: -0.1700
Data Index: 3375628 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.0371. Min Act: -0.1700
Data Index: 4810949 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.0371. Min Act: -0.1700
Data Index: 6876183 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1621. Min Range: -9.1621
Max Act: 8.0371. Min Act: -0.1700
Data Index: 7427492 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1621. Min Range: -9.1621
Max Act: 7.9746. Min Act: -0.1700
Data Index: 3191301 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1621. Min Range: -9.1621
Max Act: 7.9746. Min Act: -0.1700
Data Index: 509371 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1621. Min Range: -9.1621
Max Act: 7.9746. Min Act: -0.1700
Data Index: 6851498 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1621. Min Range: -9.1621
Max Act: 7.9121. Min Act: -0.1700
Data Index: 4225067 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1621. Min Range: -9.1621
Max Act: 7.9121. Min Act: -0.1700
Data Index: 4777717 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1621. Min Range: -9.1621
Max Act: 7.8496. Min Act: -0.1700
Data Index: 5815420 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1621. Min Range: -9.1621
Max Act: 7.8496. Min Act: -0.1700
Data Index: 8014237 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19