Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4824 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.8672. Min Act: -0.1700
Data Index: 3697820 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.8360. Min Act: -0.1700
Data Index: 1741889 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.6797. Min Act: -0.1700
Data Index: 6057121 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.6797. Min Act: -0.1700
Data Index: 5338070 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5860. Min Act: -0.1700
Data Index: 994641 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5860. Min Act: -0.1700
Data Index: 8053193 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5860. Min Act: -0.1700
Data Index: 8007483 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5860. Min Act: -0.1700
Data Index: 6727423 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5860. Min Act: -0.1700
Data Index: 7765587 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5547. Min Act: -0.1700
Data Index: 6502229 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5860. Min Act: -0.1700
Data Index: 4129985 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5547. Min Act: -0.1700
Data Index: 3997611 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5547. Min Act: -0.1700
Data Index: 8660708 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5235. Min Act: -0.1700
Data Index: 7338688 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5235. Min Act: -0.1700
Data Index: 3972718 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5235. Min Act: -0.1700
Data Index: 5191775 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.5235. Min Act: -0.1700
Data Index: 4056072 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.4922. Min Act: -0.1700
Data Index: 7619155 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.4922. Min Act: -0.1700
Data Index: 8204356 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8672. Min Range: -6.8672
Max Act: 6.4922. Min Act: -0.1700
Data Index: 449782 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19