Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4194 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.5719. Min Act: -0.1700
Data Index: 8482885 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.4466. Min Act: -0.1700
Data Index: 613213 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.4152. Min Act: -0.1700
Data Index: 782812 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.4152. Min Act: -0.1700
Data Index: 6974384 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3996. Min Act: -0.1700
Data Index: 8344010 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3996. Min Act: -0.1700
Data Index: 4930919 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3839. Min Act: -0.1700
Data Index: 8622706 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3682. Min Act: -0.1700
Data Index: 8801777 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3682. Min Act: -0.1700
Data Index: 3877591 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3525. Min Act: -0.1700
Data Index: 6165556 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3525. Min Act: -0.1700
Data Index: 1089049 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3211. Min Act: -0.1700
Data Index: 8121592 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3054. Min Act: -0.1700
Data Index: 6588066 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.3054. Min Act: -0.1700
Data Index: 7629724 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.2897. Min Act: -0.1700
Data Index: 2101787 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.2897. Min Act: -0.1700
Data Index: 7028833 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.2740. Min Act: -0.1700
Data Index: 1394683 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.2897. Min Act: -0.1700
Data Index: 7321518 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.2740. Min Act: -0.1700
Data Index: 6045414 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5719. Min Range: -3.5719
Max Act: 3.2583. Min Act: -0.1700
Data Index: 8093680 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19