Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5249 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0239. Min Range: -5.0239
Max Act: 5.0239. Min Act: -0.1700
Data Index: 3967192 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.8989. Min Act: -0.1700
Data Index: 3879392 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.8364. Min Act: -0.1700
Data Index: 8576067 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6802. Min Act: -0.1700
Data Index: 154911 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6489. Min Act: -0.1700
Data Index: 5357434 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6489. Min Act: -0.1700
Data Index: 7568721 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6489. Min Act: -0.1700
Data Index: 99921 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.5864. Min Act: -0.1700
Data Index: 1069627 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6177. Min Act: -0.1700
Data Index: 4849212 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6177. Min Act: -0.1700
Data Index: 3692276 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.6177. Min Act: -0.1700
Data Index: 2328897 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.5239. Min Act: -0.1700
Data Index: 1850592 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.5239. Min Act: -0.1700
Data Index: 446319 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.5239. Min Act: -0.1700
Data Index: 5241339 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.5239. Min Act: -0.1700
Data Index: 8751089 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.5239. Min Act: -0.1700
Data Index: 5330919 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.5239. Min Act: -0.1700
Data Index: 5635178 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.4927. Min Act: -0.1700
Data Index: 7072937 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.4927. Min Act: -0.1700
Data Index: 7105431 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0239. Min Range: -5.0239
Max Act: 4.4927. Min Act: -0.1700
Data Index: 7966802 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19