Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.8123. Min Act: -0.1700
Data Index: 1471381 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.6873. Min Act: -0.1700
Data Index: 8020710 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.5311. Min Act: -0.1700
Data Index: 8773072 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.4373. Min Act: -0.1700
Data Index: 5413959 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.4061. Min Act: -0.1700
Data Index: 1896429 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.3748. Min Act: -0.1700
Data Index: 2806922 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.3436. Min Act: -0.1700
Data Index: 7008738 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.3123. Min Act: -0.1700
Data Index: 3123867 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.2811. Min Act: -0.1700
Data Index: 8610959 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.2186. Min Act: -0.1700
Data Index: 37637 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.1873. Min Act: -0.1700
Data Index: 7575821 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.2186. Min Act: -0.1700
Data Index: 3976083 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.2186. Min Act: -0.1700
Data Index: 3380874 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.1873. Min Act: -0.1700
Data Index: 2073513 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.1873. Min Act: -0.1700
Data Index: 2639409 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.1561. Min Act: -0.1700
Data Index: 6326930 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.1561. Min Act: -0.1700
Data Index: 1346375 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.1561. Min Act: -0.1700
Data Index: 2196257 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.1248. Min Act: -0.1700
Data Index: 423539 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8123. Min Range: -7.8123
Max Act: 7.1248. Min Act: -0.1700
Data Index: 6264277 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19