Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5790 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.9080. Min Act: -0.1700
Data Index: 3406836 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.5955. Min Act: -0.1700
Data Index: 1084881 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.5330. Min Act: -0.1700
Data Index: 2279 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.5017. Min Act: -0.1700
Data Index: 1829195 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.4705. Min Act: -0.1700
Data Index: 3997506 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.3767. Min Act: -0.1700
Data Index: 1337164 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.3455. Min Act: -0.1700
Data Index: 3478296 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.3767. Min Act: -0.1700
Data Index: 1694623 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 1742486 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.3142. Min Act: -0.1700
Data Index: 5806494 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.2517. Min Act: -0.1700
Data Index: 4942510 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.2517. Min Act: -0.1700
Data Index: 4665166 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.2517. Min Act: -0.1700
Data Index: 8279474 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.2205. Min Act: -0.1700
Data Index: 7341636 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.2205. Min Act: -0.1700
Data Index: 3911281 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.2205. Min Act: -0.1700
Data Index: 3661737 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.2205. Min Act: -0.1700
Data Index: 4229176 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.2205. Min Act: -0.1700
Data Index: 1028042 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.1892. Min Act: -0.1700
Data Index: 8763310 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9080. Min Range: -5.9080
Max Act: 5.1892. Min Act: -0.1700
Data Index: 2899372 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19