Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0176. Min Range: -7.0176
Max Act: 7.0176. Min Act: -0.1700
Data Index: 6053959 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0176. Min Range: -7.0176
Max Act: 7.0176. Min Act: -0.1700
Data Index: 6225964 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.9239. Min Act: -0.1700
Data Index: 451310 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.9239. Min Act: -0.1700
Data Index: 5997540 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.8614. Min Act: -0.1700
Data Index: 3880260 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.7989. Min Act: -0.1700
Data Index: 2540889 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.7676. Min Act: -0.1700
Data Index: 1889736 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.6114. Min Act: -0.1700
Data Index: 3242683 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.6426. Min Act: -0.1700
Data Index: 6050629 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.6426. Min Act: -0.1700
Data Index: 2783198 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.5801. Min Act: -0.1700
Data Index: 361161 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.5801. Min Act: -0.1700
Data Index: 6910252 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.5801. Min Act: -0.1700
Data Index: 6263681 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.5801. Min Act: -0.1700
Data Index: 7484198 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.5489. Min Act: -0.1700
Data Index: 2488552 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.5801. Min Act: -0.1700
Data Index: 6311680 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.5176. Min Act: -0.1700
Data Index: 4070876 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.5176. Min Act: -0.1700
Data Index: 7461383 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.4864. Min Act: -0.1700
Data Index: 5200566 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0176. Min Range: -7.0176
Max Act: 6.4864. Min Act: -0.1700
Data Index: 1948124 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19