Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2964 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.9802. Min Act: -0.1700
Data Index: 5027813 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.8551. Min Act: -0.1700
Data Index: 1423178 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.8551. Min Act: -0.1700
Data Index: 910204 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.8239. Min Act: -0.1700
Data Index: 3660174 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.7926. Min Act: -0.1700
Data Index: 6486727 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.8239. Min Act: -0.1700
Data Index: 8726233 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.7613. Min Act: -0.1700
Data Index: 798458 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.7457. Min Act: -0.1700
Data Index: 1770360 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.7613. Min Act: -0.1700
Data Index: 4431859 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.7457. Min Act: -0.1700
Data Index: 1951189 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.7300. Min Act: -0.1700
Data Index: 4201776 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.7300. Min Act: -0.1700
Data Index: 5102144 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.7144. Min Act: -0.1700
Data Index: 1771978 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.6987. Min Act: -0.1700
Data Index: 1177343 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.6987. Min Act: -0.1700
Data Index: 8726234 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.7144. Min Act: -0.1700
Data Index: 3155987 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.6831. Min Act: -0.1700
Data Index: 1645119 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.6675. Min Act: -0.1700
Data Index: 6092151 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.6518. Min Act: -0.1700
Data Index: 634971 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9802. Min Range: -3.9802
Max Act: 3.6518. Min Act: -0.1700
Data Index: 351278 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19