Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4270 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1911. Min Range: -5.1911
Max Act: 5.1911. Min Act: -0.1700
Data Index: 5156357 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1911. Min Range: -5.1911
Max Act: 5.0661. Min Act: -0.1700
Data Index: 4926228 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.9724. Min Act: -0.1700
Data Index: 6747165 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.7224. Min Act: -0.1700
Data Index: 2146692 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.6911. Min Act: -0.1700
Data Index: 1365237 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.6599. Min Act: -0.1700
Data Index: 1432165 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.6599. Min Act: -0.1700
Data Index: 552570 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.6911. Min Act: -0.1700
Data Index: 2836591 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.6286. Min Act: -0.1700
Data Index: 8510148 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.6599. Min Act: -0.1700
Data Index: 971876 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.5974. Min Act: -0.1700
Data Index: 5044668 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.5661. Min Act: -0.1700
Data Index: 3716845 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.5661. Min Act: -0.1700
Data Index: 910651 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.5349. Min Act: -0.1700
Data Index: 65202 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.5349. Min Act: -0.1700
Data Index: 4757225 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.5036. Min Act: -0.1700
Data Index: 4681028 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.4724. Min Act: -0.1700
Data Index: 7905540 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.4724. Min Act: -0.1700
Data Index: 1127913 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.4724. Min Act: -0.1700
Data Index: 3420476 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1911. Min Range: -5.1911
Max Act: 4.4724. Min Act: -0.1700
Data Index: 4636676 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19