Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5441 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3056. Min Range: -7.3056
Max Act: 7.3056. Min Act: -0.1700
Data Index: 4399829 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3056. Min Range: -7.3056
Max Act: 7.1806. Min Act: -0.1700
Data Index: 5707779 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3056. Min Range: -7.3056
Max Act: 7.0244. Min Act: -0.1700
Data Index: 2045206 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3056. Min Range: -7.3056
Max Act: 7.0244. Min Act: -0.1700
Data Index: 4399830 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.9619. Min Act: -0.1700
Data Index: 1984052 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.8056. Min Act: -0.1700
Data Index: 4899131 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.8369. Min Act: -0.1700
Data Index: 903013 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.8056. Min Act: -0.1700
Data Index: 4475445 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.7119. Min Act: -0.1700
Data Index: 7310080 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.7431. Min Act: -0.1700
Data Index: 2568638 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.7119. Min Act: -0.1700
Data Index: 8324874 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.6806. Min Act: -0.1700
Data Index: 1376358 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.6494. Min Act: -0.1700
Data Index: 2602454 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.6494. Min Act: -0.1700
Data Index: 8689596 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.6494. Min Act: -0.1700
Data Index: 8372087 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.5869. Min Act: -0.1700
Data Index: 5907358 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.5869. Min Act: -0.1700
Data Index: 4964128 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.5869. Min Act: -0.1700
Data Index: 1676262 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.5556. Min Act: -0.1700
Data Index: 3138615 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3056. Min Range: -7.3056
Max Act: 6.5556. Min Act: -0.1700
Data Index: 6536171 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19