Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5563 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.5123. Min Act: -0.1700
Data Index: 2407676 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.4498. Min Act: -0.1700
Data Index: 3306284 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.3873. Min Act: -0.1700
Data Index: 3737183 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.3873. Min Act: -0.1700
Data Index: 1435450 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.2935. Min Act: -0.1700
Data Index: 6318998 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.3248. Min Act: -0.1700
Data Index: 4469542 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.3248. Min Act: -0.1700
Data Index: 5793740 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.3248. Min Act: -0.1700
Data Index: 3916247 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.2935. Min Act: -0.1700
Data Index: 4476620 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.2935. Min Act: -0.1700
Data Index: 207592 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.2623. Min Act: -0.1700
Data Index: 8593949 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.1998. Min Act: -0.1700
Data Index: 8587989 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.1998. Min Act: -0.1700
Data Index: 8556517 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.1685. Min Act: -0.1700
Data Index: 5499795 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.1685. Min Act: -0.1700
Data Index: 5077670 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.1373. Min Act: -0.1700
Data Index: 3282753 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.1685. Min Act: -0.1700
Data Index: 1256916 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.1685. Min Act: -0.1700
Data Index: 675702 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.1685. Min Act: -0.1700
Data Index: 3535029 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5123. Min Range: -5.5123
Max Act: 5.1685. Min Act: -0.1700
Data Index: 8544065 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19