Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.4089. Min Act: -0.1700
Data Index: 8630980 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.3462. Min Act: -0.1700
Data Index: 1607693 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2677. Min Act: -0.1700
Data Index: 3627581 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2991. Min Act: -0.1700
Data Index: 91537 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.1419. Min Act: -0.1700
Data Index: 7332832 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.1734. Min Act: -0.1700
Data Index: 3697530 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2677. Min Act: -0.1700
Data Index: 4255866 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2834. Min Act: -0.1700
Data Index: 3580632 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2206. Min Act: -0.1700
Data Index: 8364886 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2520. Min Act: -0.1700
Data Index: 1270154 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2206. Min Act: -0.1700
Data Index: 7829541 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2048. Min Act: -0.1700
Data Index: 987144 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2363. Min Act: -0.1700
Data Index: 7906056 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2048. Min Act: -0.1700
Data Index: 7546015 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.1891. Min Act: -0.1700
Data Index: 2031911 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2048. Min Act: -0.1700
Data Index: 5574983 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.1734. Min Act: -0.1700
Data Index: 3727685 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.1576. Min Act: -0.1700
Data Index: 5449395 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.2048. Min Act: -0.1700
Data Index: 1669087 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4089. Min Range: -3.4089
Max Act: 3.1891. Min Act: -0.1700
Data Index: 3286494 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19