Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 786 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.9136. Min Act: -0.1700
Data Index: 5293145 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.6011. Min Act: -0.1700
Data Index: 3608910 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.5386. Min Act: -0.1700
Data Index: 6954290 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.5386. Min Act: -0.1700
Data Index: 5831165 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.3824. Min Act: -0.1700
Data Index: 7797384 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.4136. Min Act: -0.1700
Data Index: 7098786 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.2886. Min Act: -0.1700
Data Index: 5057945 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.1636. Min Act: -0.1700
Data Index: 7587721 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.2261. Min Act: -0.1700
Data Index: 2309028 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.1636. Min Act: -0.1700
Data Index: 7019775 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.1949. Min Act: -0.1700
Data Index: 6354622 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.1324. Min Act: -0.1700
Data Index: 6954291 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.1011. Min Act: -0.1700
Data Index: 5456759 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.1011. Min Act: -0.1700
Data Index: 5057946 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.1011. Min Act: -0.1700
Data Index: 1768243 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.0699. Min Act: -0.1700
Data Index: 3417277 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.0699. Min Act: -0.1700
Data Index: 400386 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.0699. Min Act: -0.1700
Data Index: 3210625 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.0386. Min Act: -0.1700
Data Index: 8396377 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9136. Min Range: -7.9136
Max Act: 7.0386. Min Act: -0.1700
Data Index: 4994705 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19