Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1882. Min Act: -0.1700
Data Index: 7305389 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1882. Min Act: -0.1700
Data Index: 2132147 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1882. Min Act: -0.1700
Data Index: 997541 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1569. Min Act: -0.1700
Data Index: 5012842 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1569. Min Act: -0.1700
Data Index: 6266874 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1257. Min Act: -0.1700
Data Index: 8264940 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1257. Min Act: -0.1700
Data Index: 905598 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1257. Min Act: -0.1700
Data Index: 5406686 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1257. Min Act: -0.1700
Data Index: 7585606 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1257. Min Act: -0.1700
Data Index: 949646 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1257. Min Act: -0.1700
Data Index: 7421150 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1257. Min Act: -0.1700
Data Index: 59216 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.1257. Min Act: -0.1700
Data Index: 3540414 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.0944. Min Act: -0.1700
Data Index: 6561934 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.0944. Min Act: -0.1700
Data Index: 1049761 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.0944. Min Act: -0.1700
Data Index: 543123 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.0944. Min Act: -0.1700
Data Index: 1933413 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.0944. Min Act: -0.1700
Data Index: 818502 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.0944. Min Act: -0.1700
Data Index: 5958772 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1882. Min Range: -4.1882
Max Act: 4.0944. Min Act: -0.1700
Data Index: 5517734 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19