Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4610 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.8603. Min Act: -0.1700
Data Index: 7286118 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.8291. Min Act: -0.1700
Data Index: 6764214 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.7666. Min Act: -0.1700
Data Index: 8041181 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.7353. Min Act: -0.1700
Data Index: 826186 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.6416. Min Act: -0.1700
Data Index: 5755964 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.6416. Min Act: -0.1700
Data Index: 3561880 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.6416. Min Act: -0.1700
Data Index: 1385385 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.6103. Min Act: -0.1700
Data Index: 1667715 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.5791. Min Act: -0.1700
Data Index: 2405717 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.5478. Min Act: -0.1700
Data Index: 3052364 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.5791. Min Act: -0.1700
Data Index: 8344431 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.5791. Min Act: -0.1700
Data Index: 4617307 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.5478. Min Act: -0.1700
Data Index: 1011317 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.4853. Min Act: -0.1700
Data Index: 3052368 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.5165. Min Act: -0.1700
Data Index: 3052370 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.4853. Min Act: -0.1700
Data Index: 1667714 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.4853. Min Act: -0.1700
Data Index: 1667712 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.4853. Min Act: -0.1700
Data Index: 7201257 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.4853. Min Act: -0.1700
Data Index: 3052371 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8603. Min Range: -4.8603
Max Act: 4.4853. Min Act: -0.1700
Data Index: 3052366 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19