Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5077 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.4181. Min Act: -0.1700
Data Index: 833243 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.2930. Min Act: -0.1700
Data Index: 4919792 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.2618. Min Act: -0.1700
Data Index: 2676521 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.1055. Min Act: -0.1700
Data Index: 6266369 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0743. Min Act: -0.1700
Data Index: 8588823 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0743. Min Act: -0.1700
Data Index: 5699540 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4181. Min Range: -4.4181
Max Act: 3.9805. Min Act: -0.1700
Data Index: 2649990 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0117. Min Act: -0.1700
Data Index: 4725799 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4181. Min Range: -4.4181
Max Act: 3.9805. Min Act: -0.1700
Data Index: 1063175 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0117. Min Act: -0.1700
Data Index: 6514464 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0117. Min Act: -0.1700
Data Index: 234413 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0117. Min Act: -0.1700
Data Index: 5033895 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0117. Min Act: -0.1700
Data Index: 2594354 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0117. Min Act: -0.1700
Data Index: 8283121 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0117. Min Act: -0.1700
Data Index: 7222405 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4181. Min Range: -4.4181
Max Act: 4.0117. Min Act: -0.1700
Data Index: 5939282 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4181. Min Range: -4.4181
Max Act: 3.9805. Min Act: -0.1700
Data Index: 1610158 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4181. Min Range: -4.4181
Max Act: 3.9805. Min Act: -0.1700
Data Index: 6431561 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4181. Min Range: -4.4181
Max Act: 3.9492. Min Act: -0.1700
Data Index: 3876256 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4181. Min Range: -4.4181
Max Act: 3.9492. Min Act: -0.1700
Data Index: 3818771 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19