Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3279 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0797. Min Range: -9.0797
Max Act: 9.0797. Min Act: -0.1700
Data Index: 2466174 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.8297. Min Act: -0.1700
Data Index: 8658819 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.7672. Min Act: -0.1700
Data Index: 184844 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.7047. Min Act: -0.1700
Data Index: 5445556 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.6422. Min Act: -0.1700
Data Index: 8345363 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.6422. Min Act: -0.1700
Data Index: 8630595 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.6422. Min Act: -0.1700
Data Index: 850592 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.5797. Min Act: -0.1700
Data Index: 2975797 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.5797. Min Act: -0.1700
Data Index: 1827468 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.5797. Min Act: -0.1700
Data Index: 8768714 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.5172. Min Act: -0.1700
Data Index: 5603040 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.5172. Min Act: -0.1700
Data Index: 5659438 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.4547. Min Act: -0.1700
Data Index: 5747880 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.4547. Min Act: -0.1700
Data Index: 162266 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.4547. Min Act: -0.1700
Data Index: 1505303 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.4547. Min Act: -0.1700
Data Index: 6667188 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.3922. Min Act: -0.1700
Data Index: 2709738 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.3922. Min Act: -0.1700
Data Index: 6738990 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.3922. Min Act: -0.1700
Data Index: 2935663 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0797. Min Range: -9.0797
Max Act: 8.3922. Min Act: -0.1700
Data Index: 2450410 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19