Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1225. Min Range: -6.1225
Max Act: 6.1225. Min Act: -0.1700
Data Index: 5322820 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.5600. Min Act: -0.1700
Data Index: 2110801 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.4975. Min Act: -0.1700
Data Index: 8344811 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.4662. Min Act: -0.1700
Data Index: 8268801 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.4662. Min Act: -0.1700
Data Index: 2884732 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.4350. Min Act: -0.1700
Data Index: 5369520 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.4350. Min Act: -0.1700
Data Index: 4350952 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.4350. Min Act: -0.1700
Data Index: 5712263 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.4350. Min Act: -0.1700
Data Index: 2516706 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 2996242 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3412. Min Act: -0.1700
Data Index: 2234818 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 2140845 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 7491671 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3100. Min Act: -0.1700
Data Index: 6497379 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 6155750 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3412. Min Act: -0.1700
Data Index: 2259028 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3100. Min Act: -0.1700
Data Index: 1095552 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3100. Min Act: -0.1700
Data Index: 4709123 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3100. Min Act: -0.1700
Data Index: 5287485 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1225. Min Range: -6.1225
Max Act: 5.3100. Min Act: -0.1700
Data Index: 2778213 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19