Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4538 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3230. Min Range: -2.3230
Max Act: 2.3230. Min Act: -0.1700
Data Index: 8612535 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3230. Min Range: -2.3230
Max Act: 2.2901. Min Act: -0.1700
Data Index: 3278222 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3230. Min Range: -2.3230
Max Act: 2.0404. Min Act: -0.1700
Data Index: 41254 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3230. Min Range: -2.3230
Max Act: 2.0404. Min Act: -0.1700
Data Index: 6502636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9559. Min Act: -0.1700
Data Index: 2779089 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9389. Min Act: -0.1700
Data Index: 3613620 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9389. Min Act: -0.1700
Data Index: 5284579 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9389. Min Act: -0.1700
Data Index: 4837856 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9219. Min Act: -0.1700
Data Index: 5383127 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9049. Min Act: -0.1700
Data Index: 2226547 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9049. Min Act: -0.1700
Data Index: 4845128 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9049. Min Act: -0.1700
Data Index: 4681243 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9049. Min Act: -0.1700
Data Index: 1647464 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.9049. Min Act: -0.1700
Data Index: 4424734 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.8878. Min Act: -0.1700
Data Index: 6182538 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.8878. Min Act: -0.1700
Data Index: 5634170 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.8878. Min Act: -0.1700
Data Index: 5341560 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.8878. Min Act: -0.1700
Data Index: 4055647 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.8878. Min Act: -0.1700
Data Index: 5750929 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3230. Min Range: -2.3230
Max Act: 1.8707. Min Act: -0.1700
Data Index: 3020991 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19