Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.8201. Min Act: -0.1700
Data Index: 7691867 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6326. Min Act: -0.1700
Data Index: 1634739 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6638. Min Act: -0.1700
Data Index: 5820398 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6638. Min Act: -0.1700
Data Index: 6777586 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.5076. Min Act: -0.1700
Data Index: 8821360 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.4451. Min Act: -0.1699
Data Index: 3410123 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.4138. Min Act: -0.1700
Data Index: 6487447 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.4138. Min Act: -0.1700
Data Index: 5534926 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.3826. Min Act: -0.1700
Data Index: 3061895 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.3826. Min Act: -0.1700
Data Index: 8317938 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.3826. Min Act: -0.1700
Data Index: 4924045 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.3513. Min Act: -0.1700
Data Index: 1789567 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.3201. Min Act: -0.1700
Data Index: 1868639 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.3201. Min Act: -0.1700
Data Index: 2829388 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.2888. Min Act: -0.1700
Data Index: 2870464 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.2576. Min Act: -0.1700
Data Index: 503660 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.2576. Min Act: -0.1700
Data Index: 6334845 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.2576. Min Act: -0.1700
Data Index: 7719005 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.2263. Min Act: -0.1700
Data Index: 693194 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.1951. Min Act: -0.1700
Data Index: 4966602 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19