Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.6779. Min Act: -0.1700
Data Index: 2369001 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.6154. Min Act: -0.1700
Data Index: 510434 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.6154. Min Act: -0.1700
Data Index: 3496845 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.4904. Min Act: -0.1700
Data Index: 2203193 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.5217. Min Act: -0.1700
Data Index: 2340039 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.4904. Min Act: -0.1700
Data Index: 1260037 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.4592. Min Act: -0.1700
Data Index: 2559675 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.4279. Min Act: -0.1700
Data Index: 5762860 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.3967. Min Act: -0.1700
Data Index: 5771430 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.3342. Min Act: -0.1700
Data Index: 1092310 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.3029. Min Act: -0.1700
Data Index: 2297568 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.3029. Min Act: -0.1700
Data Index: 497370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.3029. Min Act: -0.1700
Data Index: 316185 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.2717. Min Act: -0.1700
Data Index: 8103816 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.2717. Min Act: -0.1700
Data Index: 8082200 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.2404. Min Act: -0.1700
Data Index: 3843997 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.2404. Min Act: -0.1700
Data Index: 756114 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.2717. Min Act: -0.1700
Data Index: 6225816 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.2404. Min Act: -0.1700
Data Index: 6302860 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6779. Min Range: -5.6779
Max Act: 5.2092. Min Act: -0.1700
Data Index: 3458224 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19