Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.5767. Min Act: -0.1700
Data Index: 4272800 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.6080. Min Act: -0.1700
Data Index: 4541228 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.5455. Min Act: -0.1700
Data Index: 6165625 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.5455. Min Act: -0.1700
Data Index: 2670735 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.5455. Min Act: -0.1700
Data Index: 1155959 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.5142. Min Act: -0.1700
Data Index: 8185703 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.5142. Min Act: -0.1700
Data Index: 3644004 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.4830. Min Act: -0.1700
Data Index: 4988753 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.4517. Min Act: -0.1700
Data Index: 5534821 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.4205. Min Act: -0.1700
Data Index: 1998412 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.4205. Min Act: -0.1700
Data Index: 1754947 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.4205. Min Act: -0.1700
Data Index: 2735508 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.4205. Min Act: -0.1700
Data Index: 6553727 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.3892. Min Act: -0.1700
Data Index: 4515860 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.3892. Min Act: -0.1700
Data Index: 3088215 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.3892. Min Act: -0.1700
Data Index: 2000351 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.3892. Min Act: -0.1700
Data Index: 1221363 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.3580. Min Act: -0.1700
Data Index: 4922773 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.3267. Min Act: -0.1700
Data Index: 7565506 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6080. Min Range: -5.6080
Max Act: 5.2955. Min Act: -0.1700
Data Index: 8027690 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19