Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0651. Min Range: -8.0651
Max Act: 8.0651. Min Act: -0.1700
Data Index: 6431446 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.9401. Min Act: -0.1700
Data Index: 7512517 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.8463. Min Act: -0.1700
Data Index: 2781503 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.8463. Min Act: -0.1700
Data Index: 8712831 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.7213. Min Act: -0.1700
Data Index: 1268868 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.6901. Min Act: -0.1700
Data Index: 2531646 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.6901. Min Act: -0.1700
Data Index: 1616195 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.6276. Min Act: -0.1700
Data Index: 2115095 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.6276. Min Act: -0.1700
Data Index: 3945531 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5963. Min Act: -0.1700
Data Index: 668260 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5651. Min Act: -0.1700
Data Index: 6971906 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5651. Min Act: -0.1700
Data Index: 8010691 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5651. Min Act: -0.1700
Data Index: 1539078 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5338. Min Act: -0.1700
Data Index: 7266796 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5026. Min Act: -0.1700
Data Index: 1929912 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5338. Min Act: -0.1700
Data Index: 352592 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5338. Min Act: -0.1700
Data Index: 1400058 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5338. Min Act: -0.1700
Data Index: 5485801 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5338. Min Act: -0.1700
Data Index: 6937090 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0651. Min Range: -8.0651
Max Act: 7.5026. Min Act: -0.1700
Data Index: 6144003 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19