Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 818 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2447. Min Range: -5.2447
Max Act: 5.2447. Min Act: -0.1700
Data Index: 6385654 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2447. Min Range: -5.2447
Max Act: 5.2135. Min Act: -0.1700
Data Index: 7154143 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2447. Min Range: -5.2447
Max Act: 5.0572. Min Act: -0.1700
Data Index: 6621698 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2447. Min Range: -5.2447
Max Act: 5.0572. Min Act: -0.1700
Data Index: 3290590 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2447. Min Range: -5.2447
Max Act: 5.0572. Min Act: -0.1700
Data Index: 8411629 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2447. Min Range: -5.2447
Max Act: 5.0572. Min Act: -0.1700
Data Index: 6657136 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2447. Min Range: -5.2447
Max Act: 5.0572. Min Act: -0.1700
Data Index: 6845313 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2447. Min Range: -5.2447
Max Act: 5.0260. Min Act: -0.1700
Data Index: 5137225 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9947. Min Act: -0.1700
Data Index: 1725396 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2447. Min Range: -5.2447
Max Act: 5.0260. Min Act: -0.1700
Data Index: 7393258 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9947. Min Act: -0.1700
Data Index: 2110846 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9947. Min Act: -0.1700
Data Index: 5570561 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9635. Min Act: -0.1700
Data Index: 765182 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9947. Min Act: -0.1700
Data Index: 194481 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9947. Min Act: -0.1700
Data Index: 6149617 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9635. Min Act: -0.1700
Data Index: 6531027 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9635. Min Act: -0.1700
Data Index: 4554577 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9635. Min Act: -0.1700
Data Index: 1583769 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9947. Min Act: -0.1700
Data Index: 499438 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2447. Min Range: -5.2447
Max Act: 4.9635. Min Act: -0.1700
Data Index: 4444929 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19