Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5645 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.4777. Min Act: -0.1700
Data Index: 5581184 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.2902. Min Act: -0.1700
Data Index: 1168317 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.2902. Min Act: -0.1700
Data Index: 3768071 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.2902. Min Act: -0.1700
Data Index: 8104679 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.2277. Min Act: -0.1700
Data Index: 8025826 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.2277. Min Act: -0.1700
Data Index: 399638 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.1965. Min Act: -0.1700
Data Index: 7375345 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.1652. Min Act: -0.1700
Data Index: 2426746 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.0402. Min Act: -0.1700
Data Index: 5342194 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.0402. Min Act: -0.1700
Data Index: 2104485 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.0090. Min Act: -0.1700
Data Index: 3058554 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.0402. Min Act: -0.1700
Data Index: 1842670 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4777. Min Range: -7.4777
Max Act: 7.0090. Min Act: -0.1700
Data Index: 2156738 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4777. Min Range: -7.4777
Max Act: 6.9465. Min Act: -0.1700
Data Index: 4528136 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4777. Min Range: -7.4777
Max Act: 6.9465. Min Act: -0.1700
Data Index: 768910 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4777. Min Range: -7.4777
Max Act: 6.9465. Min Act: -0.1700
Data Index: 6200733 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4777. Min Range: -7.4777
Max Act: 6.9152. Min Act: -0.1700
Data Index: 5591175 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4777. Min Range: -7.4777
Max Act: 6.8840. Min Act: -0.1700
Data Index: 1605768 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4777. Min Range: -7.4777
Max Act: 6.8527. Min Act: -0.1700
Data Index: 4241078 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4777. Min Range: -7.4777
Max Act: 6.8215. Min Act: -0.1700
Data Index: 6732240 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19