Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0527. Min Range: -4.0527
Max Act: 4.0527. Min Act: -0.1700
Data Index: 6460327 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.9590. Min Act: -0.1700
Data Index: 8437801 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.8339. Min Act: -0.1700
Data Index: 8498288 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.8339. Min Act: -0.1700
Data Index: 683215 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.7714. Min Act: -0.1700
Data Index: 3068538 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.7401. Min Act: -0.1700
Data Index: 6358862 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.7401. Min Act: -0.1700
Data Index: 3074229 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.7714. Min Act: -0.1700
Data Index: 1034091 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.7088. Min Act: -0.1700
Data Index: 6296889 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6775. Min Act: -0.1700
Data Index: 7343950 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6775. Min Act: -0.1700
Data Index: 3223173 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6462. Min Act: -0.1700
Data Index: 594796 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6462. Min Act: -0.1700
Data Index: 2173137 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6149. Min Act: -0.1700
Data Index: 4268449 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6149. Min Act: -0.1700
Data Index: 6195079 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6149. Min Act: -0.1700
Data Index: 7791231 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6149. Min Act: -0.1700
Data Index: 5923233 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6149. Min Act: -0.1700
Data Index: 1050218 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6149. Min Act: -0.1700
Data Index: 3126567 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0527. Min Range: -4.0527
Max Act: 3.6149. Min Act: -0.1700
Data Index: 8064208 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19