Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5152 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0817. Min Range: -5.0817
Max Act: 5.0817. Min Act: -0.1700
Data Index: 2368627 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0817. Min Range: -5.0817
Max Act: 5.0192. Min Act: -0.1700
Data Index: 8545586 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0817. Min Range: -5.0817
Max Act: 5.0505. Min Act: -0.1700
Data Index: 304416 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.9880. Min Act: -0.1700
Data Index: 6828891 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.9567. Min Act: -0.1700
Data Index: 8475392 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.9255. Min Act: -0.1700
Data Index: 6461204 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.9255. Min Act: -0.1700
Data Index: 6942063 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.9255. Min Act: -0.1700
Data Index: 1425793 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.9255. Min Act: -0.1700
Data Index: 7016092 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.8942. Min Act: -0.1700
Data Index: 2663152 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.8630. Min Act: -0.1700
Data Index: 724407 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.8317. Min Act: -0.1700
Data Index: 1800532 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.8005. Min Act: -0.1700
Data Index: 4489745 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.8005. Min Act: -0.1700
Data Index: 1774039 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.8005. Min Act: -0.1700
Data Index: 5867686 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.7692. Min Act: -0.1700
Data Index: 267099 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.7380. Min Act: -0.1700
Data Index: 2464409 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.7067. Min Act: -0.1700
Data Index: 6952690 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.7380. Min Act: -0.1700
Data Index: 7361876 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0817. Min Range: -5.0817
Max Act: 4.7380. Min Act: -0.1700
Data Index: 5872313 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19