Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2651 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.4948. Min Act: -0.1700
Data Index: 3844249 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.4323. Min Act: -0.1700
Data Index: 7199534 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.4323. Min Act: -0.1700
Data Index: 1361770 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.4010. Min Act: -0.1700
Data Index: 1276965 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.3385. Min Act: -0.1700
Data Index: 6828668 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.3073. Min Act: -0.1700
Data Index: 2060257 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.3385. Min Act: -0.1700
Data Index: 4436025 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.3073. Min Act: -0.1700
Data Index: 4767297 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.2760. Min Act: -0.1700
Data Index: 3631751 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.2760. Min Act: -0.1700
Data Index: 6997181 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.2760. Min Act: -0.1700
Data Index: 3895278 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.2760. Min Act: -0.1700
Data Index: 725845 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.2448. Min Act: -0.1700
Data Index: 6103397 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.2448. Min Act: -0.1700
Data Index: 4144301 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.1823. Min Act: -0.1700
Data Index: 734853 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.1823. Min Act: -0.1700
Data Index: 3810640 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.2135. Min Act: -0.1700
Data Index: 8378581 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.1823. Min Act: -0.1700
Data Index: 5052025 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.1823. Min Act: -0.1700
Data Index: 838918 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4948. Min Range: -6.4948
Max Act: 6.2135. Min Act: -0.1700
Data Index: 3431777 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19