Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5978 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.6096. Min Act: -0.1700
Data Index: 1791916 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.5783. Min Act: -0.1700
Data Index: 6246811 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.5471. Min Act: -0.1700
Data Index: 7941088 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4846. Min Act: -0.1700
Data Index: 6348742 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4846. Min Act: -0.1700
Data Index: 4012061 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4846. Min Act: -0.1700
Data Index: 3693824 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4533. Min Act: -0.1700
Data Index: 1865388 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4221. Min Act: -0.1700
Data Index: 1578471 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4221. Min Act: -0.1700
Data Index: 5462702 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4221. Min Act: -0.1700
Data Index: 6939487 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4221. Min Act: -0.1700
Data Index: 86429 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4221. Min Act: -0.1700
Data Index: 1527153 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4221. Min Act: -0.1700
Data Index: 4001389 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.3908. Min Act: -0.1700
Data Index: 5045337 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.3908. Min Act: -0.1700
Data Index: 7999315 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.3596. Min Act: -0.1700
Data Index: 7998768 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.3596. Min Act: -0.1700
Data Index: 2552101 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.3283. Min Act: -0.1700
Data Index: 8196661 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.3596. Min Act: -0.1700
Data Index: 8094164 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.2971. Min Act: -0.1700
Data Index: 2228559 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19