Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2391 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.8494. Min Act: -0.1700
Data Index: 7645502 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.7868. Min Act: -0.1700
Data Index: 7442849 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.7556. Min Act: -0.1700
Data Index: 3617198 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.6461. Min Act: -0.1700
Data Index: 6543353 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.6461. Min Act: -0.1700
Data Index: 6664849 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.6304. Min Act: -0.1700
Data Index: 1700263 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.6148. Min Act: -0.1700
Data Index: 5125226 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.6148. Min Act: -0.1700
Data Index: 7190099 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5991. Min Act: -0.1700
Data Index: 4278470 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.6148. Min Act: -0.1700
Data Index: 3457221 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5835. Min Act: -0.1700
Data Index: 4261031 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5522. Min Act: -0.1700
Data Index: 3510105 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5678. Min Act: -0.1700
Data Index: 5924174 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5678. Min Act: -0.1700
Data Index: 5322671 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5208. Min Act: -0.1700
Data Index: 6678349 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.4895. Min Act: -0.1700
Data Index: 5317719 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5522. Min Act: -0.1700
Data Index: 5916981 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5208. Min Act: -0.1700
Data Index: 5149433 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5365. Min Act: -0.1700
Data Index: 6179122 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8494. Min Range: -3.8494
Max Act: 3.5208. Min Act: -0.1700
Data Index: 3017713 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19