Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.4589. Min Act: -0.1700
Data Index: 334155 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.4589. Min Act: -0.1700
Data Index: 5763797 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.4589. Min Act: -0.1700
Data Index: 7501825 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3964. Min Act: -0.1700
Data Index: 2115046 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.4277. Min Act: -0.1700
Data Index: 7346069 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3964. Min Act: -0.1700
Data Index: 3975286 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.4277. Min Act: -0.1700
Data Index: 4736470 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3964. Min Act: -0.1700
Data Index: 2638324 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3964. Min Act: -0.1700
Data Index: 5953123 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3652. Min Act: -0.1700
Data Index: 6902639 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3339. Min Act: -0.1700
Data Index: 4397731 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3652. Min Act: -0.1700
Data Index: 7315964 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3339. Min Act: -0.1700
Data Index: 1673135 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3339. Min Act: -0.1700
Data Index: 5998179 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3339. Min Act: -0.1700
Data Index: 3026490 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3652. Min Act: -0.1700
Data Index: 1985303 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3339. Min Act: -0.1700
Data Index: 1014710 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3652. Min Act: -0.1700
Data Index: 5481188 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3652. Min Act: -0.1700
Data Index: 3992824 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4589. Min Range: -4.4589
Max Act: 4.3027. Min Act: -0.1700
Data Index: 6110169 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19