Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6357 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4384. Min Range: -6.4384
Max Act: 6.4384. Min Act: -0.1700
Data Index: 879611 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4384. Min Range: -6.4384
Max Act: 6.4384. Min Act: -0.1700
Data Index: 5189348 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4384. Min Range: -6.4384
Max Act: 6.3134. Min Act: -0.1700
Data Index: 5686870 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4384. Min Range: -6.4384
Max Act: 6.1259. Min Act: -0.1700
Data Index: 3372983 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4384. Min Range: -6.4384
Max Act: 6.1259. Min Act: -0.1700
Data Index: 295113 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4384. Min Range: -6.4384
Max Act: 6.0947. Min Act: -0.1700
Data Index: 2470160 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.9697. Min Act: -0.1700
Data Index: 820763 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.9384. Min Act: -0.1700
Data Index: 4900942 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.9384. Min Act: -0.1700
Data Index: 7572512 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.9072. Min Act: -0.1700
Data Index: 1143006 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.9072. Min Act: -0.1700
Data Index: 4113968 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.9072. Min Act: -0.1700
Data Index: 7933433 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.8759. Min Act: -0.1700
Data Index: 4900943 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.8759. Min Act: -0.1700
Data Index: 5155094 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.8759. Min Act: -0.1700
Data Index: 97352 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.8447. Min Act: -0.1700
Data Index: 6409171 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.8134. Min Act: -0.1700
Data Index: 6881161 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.8447. Min Act: -0.1700
Data Index: 5763040 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.8447. Min Act: -0.1700
Data Index: 5763041 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4384. Min Range: -6.4384
Max Act: 5.8759. Min Act: -0.1700
Data Index: 4524842 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19