Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3243 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.4192. Min Act: -0.1700
Data Index: 3539121 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.3567. Min Act: -0.1700
Data Index: 4046612 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.3567. Min Act: -0.1700
Data Index: 3738618 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.3567. Min Act: -0.1700
Data Index: 2941529 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.2942. Min Act: -0.1700
Data Index: 5007069 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.2942. Min Act: -0.1700
Data Index: 1801824 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.1692. Min Act: -0.1700
Data Index: 3461310 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.2317. Min Act: -0.1700
Data Index: 1080464 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.1692. Min Act: -0.1700
Data Index: 5043324 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.1067. Min Act: -0.1700
Data Index: 3839483 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.1067. Min Act: -0.1700
Data Index: 460290 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.1067. Min Act: -0.1700
Data Index: 5381261 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.1067. Min Act: -0.1700
Data Index: 395552 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.1067. Min Act: -0.1700
Data Index: 6285435 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.1067. Min Act: -0.1700
Data Index: 3749456 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.0442. Min Act: -0.1700
Data Index: 6427296 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.0442. Min Act: -0.1700
Data Index: 3276613 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.0442. Min Act: -0.1700
Data Index: 1393631 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4192. Min Range: -9.4192
Max Act: 9.0442. Min Act: -0.1700
Data Index: 8350135 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4192. Min Range: -9.4192
Max Act: 8.9817. Min Act: -0.1700
Data Index: 3317082 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19