Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4478 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1164. Min Range: -5.1164
Max Act: 5.1164. Min Act: -0.1700
Data Index: 297998 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1164. Min Range: -5.1164
Max Act: 5.1164. Min Act: -0.1700
Data Index: 2674567 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1164. Min Range: -5.1164
Max Act: 5.0226. Min Act: -0.1700
Data Index: 2570536 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1164. Min Range: -5.1164
Max Act: 5.0226. Min Act: -0.1700
Data Index: 2701303 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1164. Min Range: -5.1164
Max Act: 5.0226. Min Act: -0.1700
Data Index: 4285774 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.9914. Min Act: -0.1700
Data Index: 2036323 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.9601. Min Act: -0.1700
Data Index: 5253025 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8976. Min Act: -0.1700
Data Index: 2807285 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8976. Min Act: -0.1700
Data Index: 2487134 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8976. Min Act: -0.1700
Data Index: 7886389 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8976. Min Act: -0.1700
Data Index: 8111703 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8664. Min Act: -0.1700
Data Index: 4635681 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8664. Min Act: -0.1700
Data Index: 4476931 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8664. Min Act: -0.1700
Data Index: 349959 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8664. Min Act: -0.1700
Data Index: 5466780 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8664. Min Act: -0.1700
Data Index: 241807 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8664. Min Act: -0.1700
Data Index: 667420 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8664. Min Act: -0.1700
Data Index: 7024242 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8351. Min Act: -0.1700
Data Index: 7767986 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1164. Min Range: -5.1164
Max Act: 4.8351. Min Act: -0.1700
Data Index: 26970 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19