Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4413 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.3839. Min Act: -0.1700
Data Index: 4924636 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.3682. Min Act: -0.1700
Data Index: 854407 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.3368. Min Act: -0.1700
Data Index: 2377648 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.3368. Min Act: -0.1700
Data Index: 7830242 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.3211. Min Act: -0.1700
Data Index: 2171740 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.3211. Min Act: -0.1700
Data Index: 7276804 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.2897. Min Act: -0.1700
Data Index: 2771098 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.2583. Min Act: -0.1700
Data Index: 5589146 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.2269. Min Act: -0.1700
Data Index: 8677926 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.1955. Min Act: -0.1700
Data Index: 5008037 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.2112. Min Act: -0.1700
Data Index: 1782756 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.2112. Min Act: -0.1700
Data Index: 2918822 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.2269. Min Act: -0.1700
Data Index: 7500582 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.2112. Min Act: -0.1700
Data Index: 2128548 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.1955. Min Act: -0.1700
Data Index: 4485290 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.2112. Min Act: -0.1700
Data Index: 7800439 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.1955. Min Act: -0.1700
Data Index: 2036363 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.1955. Min Act: -0.1700
Data Index: 2696705 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.1797. Min Act: -0.1700
Data Index: 1641970 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3839. Min Range: -3.3839
Max Act: 3.1797. Min Act: -0.1700
Data Index: 1420431 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19