Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1933. Min Range: -6.1933
Max Act: 6.1933. Min Act: -0.1700
Data Index: 6286233 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1933. Min Range: -6.1933
Max Act: 6.0995. Min Act: -0.1700
Data Index: 1046467 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1933. Min Range: -6.1933
Max Act: 6.0995. Min Act: -0.1700
Data Index: 1874740 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1933. Min Range: -6.1933
Max Act: 6.0370. Min Act: -0.1700
Data Index: 8258348 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1933. Min Range: -6.1933
Max Act: 6.0058. Min Act: -0.1700
Data Index: 7270740 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.6620. Min Act: -0.1700
Data Index: 6667087 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.6620. Min Act: -0.1700
Data Index: 4512037 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.6620. Min Act: -0.1700
Data Index: 4133030 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.6620. Min Act: -0.1700
Data Index: 777452 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.6308. Min Act: -0.1700
Data Index: 3139295 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.6308. Min Act: -0.1700
Data Index: 7617446 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.6308. Min Act: -0.1700
Data Index: 2749556 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.6308. Min Act: -0.1700
Data Index: 7378625 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.5683. Min Act: -0.1700
Data Index: 7176457 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.5370. Min Act: -0.1700
Data Index: 517133 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.5683. Min Act: -0.1700
Data Index: 7239358 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.5370. Min Act: -0.1700
Data Index: 3392895 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.5370. Min Act: -0.1700
Data Index: 758966 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.5370. Min Act: -0.1700
Data Index: 8353582 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1933. Min Range: -6.1933
Max Act: 5.5058. Min Act: -0.1700
Data Index: 6482203 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19