Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2084. Min Range: -5.2084
Max Act: 5.2084. Min Act: -0.1700
Data Index: 5356248 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2084. Min Range: -5.2084
Max Act: 5.1146. Min Act: -0.1700
Data Index: 3989795 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2084. Min Range: -5.2084
Max Act: 5.1146. Min Act: -0.1700
Data Index: 4159114 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.8959. Min Act: -0.1700
Data Index: 2715192 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.8646. Min Act: -0.1700
Data Index: 3196601 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.8334. Min Act: -0.1700
Data Index: 6747539 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.8334. Min Act: -0.1700
Data Index: 6587244 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.8334. Min Act: -0.1700
Data Index: 3617468 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.8021. Min Act: -0.1700
Data Index: 916352 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.8021. Min Act: -0.1700
Data Index: 8582245 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7396. Min Act: -0.1700
Data Index: 2688732 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7709. Min Act: -0.1700
Data Index: 4254052 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7396. Min Act: -0.1700
Data Index: 5571101 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7709. Min Act: -0.1700
Data Index: 4512035 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7396. Min Act: -0.1700
Data Index: 328809 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7396. Min Act: -0.1700
Data Index: 1587762 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7396. Min Act: -0.1700
Data Index: 4721727 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7084. Min Act: -0.1700
Data Index: 2313143 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7084. Min Act: -0.1700
Data Index: 3124392 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2084. Min Range: -5.2084
Max Act: 4.7084. Min Act: -0.1700
Data Index: 6343759 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19