Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.8123. Min Act: -0.1700
Data Index: 8300297 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.5310. Min Act: -0.1700
Data Index: 5925513 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.5310. Min Act: -0.1700
Data Index: 8042591 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.4998. Min Act: -0.1700
Data Index: 501332 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.4373. Min Act: -0.1700
Data Index: 7953381 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.4060. Min Act: -0.1700
Data Index: 8431238 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.4060. Min Act: -0.1700
Data Index: 6246192 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.3123. Min Act: -0.1700
Data Index: 5643264 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.3123. Min Act: -0.1700
Data Index: 5912741 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.2498. Min Act: -0.1700
Data Index: 4320879 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.2185. Min Act: -0.1700
Data Index: 7926310 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.2185. Min Act: -0.1700
Data Index: 3316964 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.1873. Min Act: -0.1700
Data Index: 3547399 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.2185. Min Act: -0.1700
Data Index: 3852446 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.1873. Min Act: -0.1700
Data Index: 1843013 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.1873. Min Act: -0.1700
Data Index: 5344082 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.1560. Min Act: -0.1700
Data Index: 93368 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.1873. Min Act: -0.1700
Data Index: 7681463 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.1560. Min Act: -0.1700
Data Index: 3542811 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8123. Min Range: -5.8123
Max Act: 5.1873. Min Act: -0.1700
Data Index: 5695652 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19