Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.4624. Min Act: -0.1700
Data Index: 1015983 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.4624. Min Act: -0.1700
Data Index: 8742811 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.4311. Min Act: -0.1700
Data Index: 3966763 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.3999. Min Act: -0.1700
Data Index: 2025732 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.3999. Min Act: -0.1700
Data Index: 6491825 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.3686. Min Act: -0.1700
Data Index: 3357822 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.3686. Min Act: -0.1700
Data Index: 8802529 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.3061. Min Act: -0.1700
Data Index: 2339599 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.3061. Min Act: -0.1700
Data Index: 6625259 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2749. Min Act: -0.1700
Data Index: 4152980 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2749. Min Act: -0.1700
Data Index: 3198883 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2436. Min Act: -0.1700
Data Index: 6588209 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2749. Min Act: -0.1700
Data Index: 552227 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2436. Min Act: -0.1700
Data Index: 6302076 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2124. Min Act: -0.1700
Data Index: 7649226 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2124. Min Act: -0.1700
Data Index: 3078247 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2124. Min Act: -0.1700
Data Index: 8628479 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2124. Min Act: -0.1700
Data Index: 2991361 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2124. Min Act: -0.1700
Data Index: 8636360 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4624. Min Range: -5.4624
Max Act: 5.2124. Min Act: -0.1700
Data Index: 3998841 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19