Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.6144. Min Act: -0.1700
Data Index: 584931 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.5519. Min Act: -0.1700
Data Index: 2090563 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.5831. Min Act: -0.1700
Data Index: 5657813 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.5519. Min Act: -0.1700
Data Index: 2839577 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.5206. Min Act: -0.1700
Data Index: 42284 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.4894. Min Act: -0.1700
Data Index: 3482477 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.4581. Min Act: -0.1700
Data Index: 6132747 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.4269. Min Act: -0.1700
Data Index: 6199464 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.4581. Min Act: -0.1700
Data Index: 42285 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.4269. Min Act: -0.1700
Data Index: 6711547 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.3956. Min Act: -0.1699
Data Index: 4614051 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.4269. Min Act: -0.1700
Data Index: 42280 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.3956. Min Act: -0.1700
Data Index: 4957652 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.3644. Min Act: -0.1700
Data Index: 6335630 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.3331. Min Act: -0.1700
Data Index: 6947096 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.3331. Min Act: -0.1700
Data Index: 7082355 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.3331. Min Act: -0.1700
Data Index: 8016110 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.3019. Min Act: -0.1700
Data Index: 5652982 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.3331. Min Act: -0.1700
Data Index: 5899390 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6144. Min Range: -6.6144
Max Act: 6.3019. Min Act: -0.1700
Data Index: 2702677 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19