Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.3148. Min Act: -0.1700
Data Index: 6764056 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.1898. Min Act: -0.1700
Data Index: 6089872 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.1586. Min Act: -0.1700
Data Index: 324521 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.1273. Min Act: -0.1700
Data Index: 8743480 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.0961. Min Act: -0.1700
Data Index: 4635285 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.0961. Min Act: -0.1700
Data Index: 5094247 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.1273. Min Act: -0.1700
Data Index: 4982233 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.0648. Min Act: -0.1700
Data Index: 2395251 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.0336. Min Act: -0.1700
Data Index: 384931 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.0336. Min Act: -0.1700
Data Index: 6673395 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.0023. Min Act: -0.1700
Data Index: 4148703 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3148. Min Range: -7.3148
Max Act: 6.9711. Min Act: -0.1700
Data Index: 6631080 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3148. Min Range: -7.3148
Max Act: 7.0023. Min Act: -0.1700
Data Index: 1009156 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3148. Min Range: -7.3148
Max Act: 6.9711. Min Act: -0.1700
Data Index: 4246460 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3148. Min Range: -7.3148
Max Act: 6.9398. Min Act: -0.1700
Data Index: 765443 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3148. Min Range: -7.3148
Max Act: 6.9086. Min Act: -0.1700
Data Index: 5091685 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3148. Min Range: -7.3148
Max Act: 6.8461. Min Act: -0.1700
Data Index: 4404494 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3148. Min Range: -7.3148
Max Act: 6.8461. Min Act: -0.1700
Data Index: 6358230 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3148. Min Range: -7.3148
Max Act: 6.8461. Min Act: -0.1700
Data Index: 8043188 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3148. Min Range: -7.3148
Max Act: 6.8461. Min Act: -0.1700
Data Index: 8489757 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19