Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6332 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.5615. Min Act: -0.1700
Data Index: 7565839 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.4990. Min Act: -0.1700
Data Index: 4183152 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.3427. Min Act: -0.1700
Data Index: 5797559 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.3115. Min Act: -0.1700
Data Index: 1188212 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.2802. Min Act: -0.1700
Data Index: 7026811 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.2490. Min Act: -0.1700
Data Index: 8142014 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.2177. Min Act: -0.1700
Data Index: 6306076 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.2490. Min Act: -0.1700
Data Index: 8722758 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.2490. Min Act: -0.1700
Data Index: 6904125 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.1240. Min Act: -0.1700
Data Index: 7784283 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0927. Min Act: -0.1700
Data Index: 1948177 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0927. Min Act: -0.1700
Data Index: 1299976 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0927. Min Act: -0.1700
Data Index: 6638101 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0927. Min Act: -0.1700
Data Index: 3277406 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0927. Min Act: -0.1700
Data Index: 8479268 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0927. Min Act: -0.1700
Data Index: 1783147 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0927. Min Act: -0.1700
Data Index: 3560121 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0927. Min Act: -0.1700
Data Index: 4852589 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0927. Min Act: -0.1700
Data Index: 849716 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5615. Min Range: -7.5615
Max Act: 7.0615. Min Act: -0.1700
Data Index: 4828011 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19