Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3955 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.9862. Min Act: -0.1700
Data Index: 3244199 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.8612. Min Act: -0.1700
Data Index: 5793928 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.8612. Min Act: -0.1700
Data Index: 8579202 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7674. Min Act: -0.1700
Data Index: 4460119 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7674. Min Act: -0.1700
Data Index: 179878 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7362. Min Act: -0.1700
Data Index: 172289 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7362. Min Act: -0.1700
Data Index: 8053085 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7362. Min Act: -0.1700
Data Index: 51869 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7049. Min Act: -0.1700
Data Index: 2080363 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7362. Min Act: -0.1700
Data Index: 4419208 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7049. Min Act: -0.1700
Data Index: 7814275 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6737. Min Act: -0.1700
Data Index: 4596981 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6737. Min Act: -0.1700
Data Index: 1866598 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7049. Min Act: -0.1700
Data Index: 1239256 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6737. Min Act: -0.1700
Data Index: 1769285 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.7049. Min Act: -0.1700
Data Index: 2818705 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6737. Min Act: -0.1700
Data Index: 2439913 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6737. Min Act: -0.1700
Data Index: 7490038 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6424. Min Act: -0.1700
Data Index: 5891593 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9862. Min Range: -5.9862
Max Act: 5.6424. Min Act: -0.1700
Data Index: 7484862 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19