Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.8198. Min Act: -0.1700
Data Index: 911872 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.5073. Min Act: -0.1700
Data Index: 784220 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.5073. Min Act: -0.1700
Data Index: 5787628 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.4448. Min Act: -0.1700
Data Index: 3560486 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.4448. Min Act: -0.1700
Data Index: 2006804 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.4448. Min Act: -0.1700
Data Index: 113646 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.3823. Min Act: -0.1700
Data Index: 328199 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.3823. Min Act: -0.1700
Data Index: 1899753 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.3823. Min Act: -0.1700
Data Index: 162987 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.3198. Min Act: -0.1700
Data Index: 8494981 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.3198. Min Act: -0.1700
Data Index: 2617947 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.3198. Min Act: -0.1700
Data Index: 1517230 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.3198. Min Act: -0.1700
Data Index: 2571286 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.2886. Min Act: -0.1700
Data Index: 5956894 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.3198. Min Act: -0.1700
Data Index: 1450431 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.2886. Min Act: -0.1700
Data Index: 7590001 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.2886. Min Act: -0.1700
Data Index: 8470333 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.2886. Min Act: -0.1700
Data Index: 50150 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.2886. Min Act: -0.1700
Data Index: 8561260 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8198. Min Range: -6.8198
Max Act: 6.2573. Min Act: -0.1700
Data Index: 2367570 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19