Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1362 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.7225. Min Act: -0.1700
Data Index: 8058599 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.7065. Min Act: -0.1700
Data Index: 5181649 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6745. Min Act: -0.1700
Data Index: 692833 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6905. Min Act: -0.1700
Data Index: 1308215 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6905. Min Act: -0.1700
Data Index: 6025743 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6745. Min Act: -0.1700
Data Index: 1823113 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6745. Min Act: -0.1700
Data Index: 1968621 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6584. Min Act: -0.1700
Data Index: 4678904 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6745. Min Act: -0.1700
Data Index: 4446692 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6745. Min Act: -0.1700
Data Index: 2519107 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6745. Min Act: -0.1700
Data Index: 3149350 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6584. Min Act: -0.1700
Data Index: 6237237 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6745. Min Act: -0.1700
Data Index: 6409334 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6584. Min Act: -0.1700
Data Index: 8207795 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6584. Min Act: -0.1700
Data Index: 3539395 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6584. Min Act: -0.1700
Data Index: 1406832 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6584. Min Act: -0.1700
Data Index: 7210201 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6584. Min Act: -0.1700
Data Index: 5553297 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6745. Min Act: -0.1700
Data Index: 2685603 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6584. Min Act: -0.1700
Data Index: 1288723 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19