Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1056 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.1121. Min Act: -0.1700
Data Index: 4936444 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0806. Min Act: -0.1700
Data Index: 6102801 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0649. Min Act: -0.1700
Data Index: 5161137 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0649. Min Act: -0.1700
Data Index: 7329925 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0649. Min Act: -0.1700
Data Index: 8657250 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0333. Min Act: -0.1700
Data Index: 4606965 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0175. Min Act: -0.1700
Data Index: 4185757 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0175. Min Act: -0.1700
Data Index: 3796848 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0175. Min Act: -0.1700
Data Index: 2591678 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0175. Min Act: -0.1700
Data Index: 4013078 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0175. Min Act: -0.1700
Data Index: 5674704 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0017. Min Act: -0.1700
Data Index: 7742307 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0017. Min Act: -0.1700
Data Index: 7927220 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1121. Min Range: -3.1121
Max Act: 3.0175. Min Act: -0.1700
Data Index: 7241651 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1121. Min Range: -3.1121
Max Act: 2.9859. Min Act: -0.1700
Data Index: 180671 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1121. Min Range: -3.1121
Max Act: 2.9859. Min Act: -0.1700
Data Index: 5861590 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1121. Min Range: -3.1121
Max Act: 2.9859. Min Act: -0.1700
Data Index: 8476332 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1121. Min Range: -3.1121
Max Act: 2.9859. Min Act: -0.1700
Data Index: 3845952 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1121. Min Range: -3.1121
Max Act: 2.9701. Min Act: -0.1700
Data Index: 4185760 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1121. Min Range: -3.1121
Max Act: 2.9701. Min Act: -0.1700
Data Index: 134360 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19