Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.4532. Min Act: -0.1700
Data Index: 1095445 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.4061. Min Act: -0.1700
Data Index: 470302 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.4061. Min Act: -0.1700
Data Index: 3836775 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.3748. Min Act: -0.1700
Data Index: 8358519 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.3434. Min Act: -0.1700
Data Index: 2000741 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.2649. Min Act: -0.1700
Data Index: 1555409 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.2492. Min Act: -0.1700
Data Index: 6492414 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.2178. Min Act: -0.1700
Data Index: 1670986 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.2021. Min Act: -0.1700
Data Index: 2569281 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.2021. Min Act: -0.1700
Data Index: 5029935 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.1863. Min Act: -0.1700
Data Index: 6347677 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.1863. Min Act: -0.1700
Data Index: 5687659 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.1706. Min Act: -0.1700
Data Index: 3238157 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.2021. Min Act: -0.1700
Data Index: 309100 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.1863. Min Act: -0.1700
Data Index: 3238158 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.1863. Min Act: -0.1700
Data Index: 4684990 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.1863. Min Act: -0.1700
Data Index: 6233387 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.1706. Min Act: -0.1700
Data Index: 2100156 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.1706. Min Act: -0.1700
Data Index: 1792814 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4532. Min Range: -3.4532
Max Act: 3.1549. Min Act: -0.1700
Data Index: 3696214 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19