Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1219. Min Range: -9.1219
Max Act: 9.1219. Min Act: -0.1700
Data Index: 6152874 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.9969. Min Act: -0.1700
Data Index: 7826577 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.8094. Min Act: -0.1700
Data Index: 5507245 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.7469. Min Act: -0.1700
Data Index: 836089 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.6844. Min Act: -0.1700
Data Index: 815760 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.5594. Min Act: -0.1700
Data Index: 8200656 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.4969. Min Act: -0.1700
Data Index: 4861969 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.4344. Min Act: -0.1700
Data Index: 3205181 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.3719. Min Act: -0.1700
Data Index: 5834389 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.3719. Min Act: -0.1700
Data Index: 3906273 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.3719. Min Act: -0.1700
Data Index: 6773825 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.2469. Min Act: -0.1700
Data Index: 3369636 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.3094. Min Act: -0.1700
Data Index: 3738410 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.3094. Min Act: -0.1700
Data Index: 6013254 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.1844. Min Act: -0.1700
Data Index: 8710310 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.1219. Min Act: -0.1700
Data Index: 7126285 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.1219. Min Act: -0.1700
Data Index: 4180940 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.1219. Min Act: -0.1700
Data Index: 6445554 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1219. Min Range: -9.1219
Max Act: 8.1219. Min Act: -0.1700
Data Index: 1807797 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1219. Min Range: -9.1219
Max Act: 7.9969. Min Act: -0.1700
Data Index: 451180 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19