Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.7669. Min Act: -0.1700
Data Index: 2618747 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.2981. Min Act: -0.1700
Data Index: 2954702 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.1419. Min Act: -0.1700
Data Index: 7521840 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.1106. Min Act: -0.1700
Data Index: 2334042 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.1419. Min Act: -0.1700
Data Index: 7194336 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.1106. Min Act: -0.1700
Data Index: 4621341 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.1106. Min Act: -0.1700
Data Index: 2003059 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.0794. Min Act: -0.1700
Data Index: 2197832 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.0794. Min Act: -0.1700
Data Index: 7535042 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.0794. Min Act: -0.1700
Data Index: 4650315 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.0169. Min Act: -0.1699
Data Index: 2575905 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7669. Min Range: -7.7669
Max Act: 6.9856. Min Act: -0.1700
Data Index: 7706022 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7669. Min Range: -7.7669
Max Act: 6.9856. Min Act: -0.1700
Data Index: 3942781 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7669. Min Range: -7.7669
Max Act: 6.9856. Min Act: -0.1700
Data Index: 7627910 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.0169. Min Act: -0.1700
Data Index: 1289879 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7669. Min Range: -7.7669
Max Act: 6.9856. Min Act: -0.1700
Data Index: 2616787 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7669. Min Range: -7.7669
Max Act: 6.9856. Min Act: -0.1700
Data Index: 6567426 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7669. Min Range: -7.7669
Max Act: 6.9231. Min Act: -0.1700
Data Index: 3706066 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7669. Min Range: -7.7669
Max Act: 6.9544. Min Act: -0.1700
Data Index: 6413059 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7669. Min Range: -7.7669
Max Act: 6.9544. Min Act: -0.1700
Data Index: 2456261 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19