Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5333 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.9220. Min Act: -0.1700
Data Index: 5744633 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.6720. Min Act: -0.1700
Data Index: 7428348 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.6095. Min Act: -0.1700
Data Index: 6550768 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.5470. Min Act: -0.1700
Data Index: 5344149 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.5470. Min Act: -0.1700
Data Index: 6187596 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.4845. Min Act: -0.1700
Data Index: 8304750 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.4533. Min Act: -0.1700
Data Index: 7760044 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.4220. Min Act: -0.1700
Data Index: 8281352 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.3908. Min Act: -0.1700
Data Index: 7646824 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.2658. Min Act: -0.1700
Data Index: 4431435 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.2658. Min Act: -0.1700
Data Index: 5699952 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.2658. Min Act: -0.1700
Data Index: 3567456 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.2658. Min Act: -0.1700
Data Index: 7270005 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.2033. Min Act: -0.1700
Data Index: 7178828 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.2033. Min Act: -0.1700
Data Index: 3711675 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.1720. Min Act: -0.1700
Data Index: 154958 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.1720. Min Act: -0.1700
Data Index: 2034766 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.1408. Min Act: -0.1700
Data Index: 8706695 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.0783. Min Act: -0.1700
Data Index: 6233508 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9220. Min Range: -7.9220
Max Act: 7.0783. Min Act: -0.1700
Data Index: 3630447 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19