Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.7177. Min Act: -0.1700
Data Index: 8530178 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.7177. Min Act: -0.1700
Data Index: 4499234 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.6864. Min Act: -0.1700
Data Index: 6122778 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.7177. Min Act: -0.1700
Data Index: 8561337 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.6552. Min Act: -0.1700
Data Index: 6673918 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.6239. Min Act: -0.1700
Data Index: 1903370 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.5927. Min Act: -0.1700
Data Index: 4981361 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.5614. Min Act: -0.1700
Data Index: 7256956 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.5614. Min Act: -0.1700
Data Index: 688789 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.5302. Min Act: -0.1700
Data Index: 969710 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4677. Min Act: -0.1700
Data Index: 6570923 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4989. Min Act: -0.1700
Data Index: 2521061 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4989. Min Act: -0.1700
Data Index: 2243249 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4677. Min Act: -0.1700
Data Index: 4749844 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4677. Min Act: -0.1700
Data Index: 6948966 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4364. Min Act: -0.1700
Data Index: 5368673 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4364. Min Act: -0.1700
Data Index: 3087772 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4677. Min Act: -0.1700
Data Index: 3353815 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4052. Min Act: -0.1700
Data Index: 8497744 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7177. Min Range: -6.7177
Max Act: 6.4052. Min Act: -0.1700
Data Index: 1645979 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19