Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4067 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.9547. Min Act: -0.1700
Data Index: 4272769 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.5172. Min Act: -0.1700
Data Index: 4272959 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.2672. Min Act: -0.1700
Data Index: 6923898 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.2047. Min Act: -0.1700
Data Index: 3222965 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.2672. Min Act: -0.1700
Data Index: 3929823 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0797. Min Act: -0.1700
Data Index: 3255392 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0797. Min Act: -0.1700
Data Index: 3095270 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0797. Min Act: -0.1700
Data Index: 8301962 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0172. Min Act: -0.1700
Data Index: 6702537 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0172. Min Act: -0.1700
Data Index: 2647974 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9547. Min Range: -9.9547
Max Act: 9.0172. Min Act: -0.1700
Data Index: 6468463 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 2322343 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 1990525 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 3558278 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 5036449 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8297. Min Act: -0.1700
Data Index: 5260973 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 8144508 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8922. Min Act: -0.1700
Data Index: 4101416 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8922. Min Act: -0.1700
Data Index: 2179656 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9547. Min Range: -9.9547
Max Act: 8.8297. Min Act: -0.1700
Data Index: 3308614 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19