Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2683 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5190. Min Range: -10.5190
Max Act: 10.5190. Min Act: -0.1700
Data Index: 830265 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.8940. Min Act: -0.1700
Data Index: 3713566 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.5815. Min Act: -0.1700
Data Index: 8211588 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.5190. Min Act: -0.1700
Data Index: 6757047 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.5190. Min Act: -0.1700
Data Index: 7510765 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.4565. Min Act: -0.1700
Data Index: 6805418 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.4565. Min Act: -0.1700
Data Index: 5059805 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.3940. Min Act: -0.1700
Data Index: 6517023 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.3940. Min Act: -0.1700
Data Index: 633989 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.3940. Min Act: -0.1700
Data Index: 237021 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.3315. Min Act: -0.1700
Data Index: 1615047 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.3315. Min Act: -0.1700
Data Index: 2798073 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.3315. Min Act: -0.1700
Data Index: 4278665 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.2690. Min Act: -0.1700
Data Index: 2515256 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.2690. Min Act: -0.1700
Data Index: 3520377 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.2690. Min Act: -0.1700
Data Index: 1904442 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.2690. Min Act: -0.1700
Data Index: 1267641 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.2690. Min Act: -0.1700
Data Index: 2204926 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.2065. Min Act: -0.1700
Data Index: 6226561 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5190. Min Range: -10.5190
Max Act: 9.2065. Min Act: -0.1700
Data Index: 3043777 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19