Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.8845. Min Act: -0.1700
Data Index: 3784454 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6970. Min Act: -0.1700
Data Index: 6382462 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6970. Min Act: -0.1700
Data Index: 6212147 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6657. Min Act: -0.1700
Data Index: 514193 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6657. Min Act: -0.1700
Data Index: 3073532 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6657. Min Act: -0.1700
Data Index: 4623833 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6345. Min Act: -0.1700
Data Index: 3635737 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6657. Min Act: -0.1700
Data Index: 7568188 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6345. Min Act: -0.1700
Data Index: 8010880 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1698
Data Index: 835092 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1700
Data Index: 5096865 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1700
Data Index: 2823784 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1700
Data Index: 8401082 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1700
Data Index: 2472172 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1700
Data Index: 5705017 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1700
Data Index: 4100935 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1700
Data Index: 2566162 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1700
Data Index: 6824700 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.6032. Min Act: -0.1700
Data Index: 1257938 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8845. Min Range: -4.8845
Max Act: 4.5720. Min Act: -0.1700
Data Index: 1735189 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19