Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5760 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.4152. Min Act: -0.1700
Data Index: 2619534 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.2277. Min Act: -0.1700
Data Index: 8164372 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1965. Min Act: -0.1700
Data Index: 2908604 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1652. Min Act: -0.1700
Data Index: 1541335 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1652. Min Act: -0.1700
Data Index: 1179829 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1652. Min Act: -0.1700
Data Index: 2869344 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1339. Min Act: -0.1700
Data Index: 3546385 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1027. Min Act: -0.1700
Data Index: 4554094 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1027. Min Act: -0.1700
Data Index: 7104917 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1027. Min Act: -0.1700
Data Index: 6088134 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1027. Min Act: -0.1700
Data Index: 7908285 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.1027. Min Act: -0.1700
Data Index: 4056357 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.0714. Min Act: -0.1700
Data Index: 6053422 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.0714. Min Act: -0.1700
Data Index: 3126629 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.0714. Min Act: -0.1700
Data Index: 1375726 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.0714. Min Act: -0.1700
Data Index: 5030994 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.0714. Min Act: -0.1700
Data Index: 7776092 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.0402. Min Act: -0.1700
Data Index: 6872992 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.0402. Min Act: -0.1700
Data Index: 2728953 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4152. Min Range: -4.4152
Max Act: 4.0402. Min Act: -0.1700
Data Index: 7475103 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19