Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5030 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.4149. Min Act: -0.1700
Data Index: 499688 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.4149. Min Act: -0.1700
Data Index: 8831511 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3823. Min Act: -0.1700
Data Index: 827049 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3659. Min Act: -0.1700
Data Index: 1189075 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3495. Min Act: -0.1700
Data Index: 3951596 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3495. Min Act: -0.1700
Data Index: 3380670 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3167. Min Act: -0.1700
Data Index: 20055 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3167. Min Act: -0.1700
Data Index: 3992815 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3167. Min Act: -0.1700
Data Index: 4818129 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3167. Min Act: -0.1700
Data Index: 427501 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3003. Min Act: -0.1700
Data Index: 7685173 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3003. Min Act: -0.1700
Data Index: 3015499 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3003. Min Act: -0.1700
Data Index: 7698102 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3167. Min Act: -0.1700
Data Index: 91261 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3003. Min Act: -0.1700
Data Index: 1600217 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3003. Min Act: -0.1700
Data Index: 5733906 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.3003. Min Act: -0.1700
Data Index: 3359381 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.2838. Min Act: -0.1700
Data Index: 2680350 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.2838. Min Act: -0.1700
Data Index: 7966423 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4149. Min Range: -2.4149
Max Act: 2.2838. Min Act: -0.1700
Data Index: 8412948 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19