Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 178 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.7907. Min Act: -0.1700
Data Index: 6181887 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.8220. Min Act: -0.1700
Data Index: 3253421 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.8220. Min Act: -0.1700
Data Index: 5631212 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.7907. Min Act: -0.1700
Data Index: 5626678 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.6970. Min Act: -0.1700
Data Index: 317840 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.7282. Min Act: -0.1700
Data Index: 8616416 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.6970. Min Act: -0.1700
Data Index: 3188295 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.6657. Min Act: -0.1700
Data Index: 6706492 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.6345. Min Act: -0.1700
Data Index: 1951708 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.6657. Min Act: -0.1700
Data Index: 6056542 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.6032. Min Act: -0.1700
Data Index: 7996154 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.6345. Min Act: -0.1700
Data Index: 5613480 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.6032. Min Act: -0.1700
Data Index: 4343441 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.5720. Min Act: -0.1700
Data Index: 6206851 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.5720. Min Act: -0.1700
Data Index: 5828230 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.5407. Min Act: -0.1700
Data Index: 3667123 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.5407. Min Act: -0.1700
Data Index: 4513141 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.4782. Min Act: -0.1700
Data Index: 3258335 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.5407. Min Act: -0.1700
Data Index: 7916411 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8220. Min Range: -6.8220
Max Act: 6.5095. Min Act: -0.1700
Data Index: 5447427 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19