Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 556 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.5248. Min Act: -0.1700
Data Index: 5662128 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.3837. Min Act: -0.1700
Data Index: 4734961 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.3837. Min Act: -0.1700
Data Index: 895378 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.3524. Min Act: -0.1700
Data Index: 8384062 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.3053. Min Act: -0.1700
Data Index: 465528 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.2896. Min Act: -0.1700
Data Index: 254140 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.2896. Min Act: -0.1700
Data Index: 7029569 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.2425. Min Act: -0.1700
Data Index: 92048 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.2425. Min Act: -0.1700
Data Index: 3840940 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.2582. Min Act: -0.1700
Data Index: 4836352 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.2425. Min Act: -0.1700
Data Index: 5080893 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.2268. Min Act: -0.1700
Data Index: 3327387 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.1953. Min Act: -0.1700
Data Index: 3189310 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.2110. Min Act: -0.1700
Data Index: 5844198 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.1953. Min Act: -0.1700
Data Index: 7813681 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.1953. Min Act: -0.1700
Data Index: 3836502 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.1796. Min Act: -0.1700
Data Index: 6374407 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.1796. Min Act: -0.1700
Data Index: 1855054 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.1796. Min Act: -0.1700
Data Index: 8726178 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5248. Min Range: -3.5248
Max Act: 3.1796. Min Act: -0.1700
Data Index: 7534677 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19