Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1353 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.9408. Min Act: -0.1700
Data Index: 4190780 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.9408. Min Act: -0.1700
Data Index: 3569519 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.8158. Min Act: -0.1700
Data Index: 7989271 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.7846. Min Act: -0.1700
Data Index: 8040587 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.7533. Min Act: -0.1700
Data Index: 3453302 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.7533. Min Act: -0.1700
Data Index: 7062053 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.6283. Min Act: -0.1700
Data Index: 3831189 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.6596. Min Act: -0.1700
Data Index: 4643838 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.6596. Min Act: -0.1700
Data Index: 4400418 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5971. Min Act: -0.1700
Data Index: 1404992 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.6283. Min Act: -0.1700
Data Index: 2114965 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5971. Min Act: -0.1700
Data Index: 6130103 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5971. Min Act: -0.1700
Data Index: 1847750 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5971. Min Act: -0.1700
Data Index: 8719722 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5971. Min Act: -0.1700
Data Index: 5320377 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5658. Min Act: -0.1700
Data Index: 6178046 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5346. Min Act: -0.1700
Data Index: 3438718 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5658. Min Act: -0.1700
Data Index: 5735715 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5971. Min Act: -0.1700
Data Index: 8415871 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9408. Min Range: -4.9408
Max Act: 4.5658. Min Act: -0.1700
Data Index: 2809873 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19