Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6264 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.3517. Min Act: -0.1700
Data Index: 7420760 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.3205. Min Act: -0.1700
Data Index: 8099297 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.2580. Min Act: -0.1700
Data Index: 3125238 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.2267. Min Act: -0.1700
Data Index: 5065971 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.1955. Min Act: -0.1700
Data Index: 6046375 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.2267. Min Act: -0.1700
Data Index: 6048950 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.1955. Min Act: -0.1700
Data Index: 7630610 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.1955. Min Act: -0.1700
Data Index: 6365292 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.1642. Min Act: -0.1700
Data Index: 6118209 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.1642. Min Act: -0.1700
Data Index: 366367 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.1330. Min Act: -0.1700
Data Index: 4574831 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.1330. Min Act: -0.1700
Data Index: 2676550 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.1330. Min Act: -0.1700
Data Index: 4496090 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.1017. Min Act: -0.1700
Data Index: 5777931 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.0705. Min Act: -0.1700
Data Index: 6810202 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.0705. Min Act: -0.1700
Data Index: 7552236 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.0392. Min Act: -0.1700
Data Index: 84939 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.0392. Min Act: -0.1700
Data Index: 3757175 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.0392. Min Act: -0.1700
Data Index: 1487688 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3517. Min Range: -5.3517
Max Act: 5.0392. Min Act: -0.1700
Data Index: 2505090 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19