Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1940 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4711. Min Range: -6.4711
Max Act: 6.4711. Min Act: -0.1700
Data Index: 5929115 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4711. Min Range: -6.4711
Max Act: 6.4086. Min Act: -0.1700
Data Index: 2141909 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4711. Min Range: -6.4711
Max Act: 6.2523. Min Act: -0.1700
Data Index: 4556989 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4711. Min Range: -6.4711
Max Act: 6.0961. Min Act: -0.1700
Data Index: 3631186 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4711. Min Range: -6.4711
Max Act: 6.0336. Min Act: -0.1700
Data Index: 4528692 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.9086. Min Act: -0.1700
Data Index: 675765 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.9398. Min Act: -0.1700
Data Index: 2044912 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.8461. Min Act: -0.1700
Data Index: 4091570 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.6898. Min Act: -0.1700
Data Index: 540615 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.6898. Min Act: -0.1700
Data Index: 2848919 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.6273. Min Act: -0.1700
Data Index: 6343822 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.6273. Min Act: -0.1700
Data Index: 960085 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.6273. Min Act: -0.1700
Data Index: 5824435 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.6273. Min Act: -0.1700
Data Index: 5004462 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.5648. Min Act: -0.1700
Data Index: 2780163 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.5648. Min Act: -0.1700
Data Index: 2423313 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.5023. Min Act: -0.1700
Data Index: 3537012 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.5023. Min Act: -0.1700
Data Index: 5107292 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.4711. Min Act: -0.1700
Data Index: 135655 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4711. Min Range: -6.4711
Max Act: 5.4398. Min Act: -0.1700
Data Index: 5116620 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19