Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5987. Min Range: -8.5987
Max Act: 8.5987. Min Act: -0.1700
Data Index: 5860552 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5987. Min Range: -8.5987
Max Act: 8.3487. Min Act: -0.1700
Data Index: 5042778 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5987. Min Range: -8.5987
Max Act: 8.1300. Min Act: -0.1700
Data Index: 3454679 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.9112. Min Act: -0.1700
Data Index: 1896888 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.7862. Min Act: -0.1700
Data Index: 3377559 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.5987. Min Act: -0.1700
Data Index: 1152382 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.5987. Min Act: -0.1700
Data Index: 2765914 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.5987. Min Act: -0.1700
Data Index: 3546348 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.5675. Min Act: -0.1700
Data Index: 1804068 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.5675. Min Act: -0.1700
Data Index: 6527949 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.5050. Min Act: -0.1700
Data Index: 2144213 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.5362. Min Act: -0.1700
Data Index: 262278 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.5050. Min Act: -0.1700
Data Index: 5201356 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.4737. Min Act: -0.1700
Data Index: 858799 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.4425. Min Act: -0.1700
Data Index: 8243014 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.3800. Min Act: -0.1700
Data Index: 1704155 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.3800. Min Act: -0.1700
Data Index: 1428245 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.3800. Min Act: -0.1700
Data Index: 1034348 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.3800. Min Act: -0.1700
Data Index: 13625 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5987. Min Range: -8.5987
Max Act: 7.3800. Min Act: -0.1700
Data Index: 2655048 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19