Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4752 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.9327. Min Act: -0.1700
Data Index: 7589255 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.8702. Min Act: -0.1700
Data Index: 5403039 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.7764. Min Act: -0.1700
Data Index: 5912819 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.7452. Min Act: -0.1700
Data Index: 8645353 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.6827. Min Act: -0.1700
Data Index: 3746024 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.6514. Min Act: -0.1700
Data Index: 3967843 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.6827. Min Act: -0.1700
Data Index: 3231237 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.6514. Min Act: -0.1700
Data Index: 7040994 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.5889. Min Act: -0.1700
Data Index: 5088795 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.6202. Min Act: -0.1700
Data Index: 4218442 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.5889. Min Act: -0.1700
Data Index: 8132281 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.5577. Min Act: -0.1700
Data Index: 6281506 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.5264. Min Act: -0.1700
Data Index: 7468150 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.4952. Min Act: -0.1700
Data Index: 1124737 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.4952. Min Act: -0.1700
Data Index: 5585208 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.4639. Min Act: -0.1700
Data Index: 3724044 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.4952. Min Act: -0.1700
Data Index: 2364795 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.4639. Min Act: -0.1700
Data Index: 878305 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.4639. Min Act: -0.1700
Data Index: 7563136 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9327. Min Range: -6.9327
Max Act: 6.4639. Min Act: -0.1700
Data Index: 7047096 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19