Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6155 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.9786. Min Act: -0.1700
Data Index: 3257086 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.8536. Min Act: -0.1700
Data Index: 4678796 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.8224. Min Act: -0.1700
Data Index: 8441380 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.8224. Min Act: -0.1700
Data Index: 4861918 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.7911. Min Act: -0.1700
Data Index: 5928530 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.7911. Min Act: -0.1700
Data Index: 972032 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.7599. Min Act: -0.1700
Data Index: 1868296 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.6974. Min Act: -0.1700
Data Index: 1703390 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.6661. Min Act: -0.1700
Data Index: 7665499 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.6661. Min Act: -0.1700
Data Index: 2763583 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.6974. Min Act: -0.1700
Data Index: 6932731 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.6661. Min Act: -0.1700
Data Index: 5996174 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.6349. Min Act: -0.1700
Data Index: 8522199 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.6661. Min Act: -0.1700
Data Index: 2807288 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.6349. Min Act: -0.1700
Data Index: 5400525 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.6036. Min Act: -0.1700
Data Index: 8612162 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.5411. Min Act: -0.1700
Data Index: 152763 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.5411. Min Act: -0.1700
Data Index: 6590407 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.5724. Min Act: -0.1700
Data Index: 5644648 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9786. Min Range: -7.9786
Max Act: 7.5099. Min Act: -0.1700
Data Index: 2552913 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19