Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2887 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.8613. Min Act: -0.1700
Data Index: 707184 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.8301. Min Act: -0.1700
Data Index: 1710282 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.8613. Min Act: -0.1700
Data Index: 6651412 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.8301. Min Act: -0.1700
Data Index: 2438616 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7676. Min Act: -0.1700
Data Index: 4125333 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7676. Min Act: -0.1700
Data Index: 1108160 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7676. Min Act: -0.1700
Data Index: 1652453 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7676. Min Act: -0.1700
Data Index: 5043176 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7676. Min Act: -0.1700
Data Index: 697866 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7363. Min Act: -0.1700
Data Index: 4621955 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7363. Min Act: -0.1700
Data Index: 5060988 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7051. Min Act: -0.1700
Data Index: 7184185 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7051. Min Act: -0.1700
Data Index: 6694477 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.7051. Min Act: -0.1700
Data Index: 7719721 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.6426. Min Act: -0.1700
Data Index: 1864420 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.6738. Min Act: -0.1700
Data Index: 7166354 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.6426. Min Act: -0.1700
Data Index: 1128137 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.6426. Min Act: -0.1700
Data Index: 4932037 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.6738. Min Act: -0.1700
Data Index: 5354465 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8613. Min Range: -5.8613
Max Act: 5.6738. Min Act: -0.1700
Data Index: 6518206 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19