Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.9170. Min Act: -0.1700
Data Index: 8168229 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.7607. Min Act: -0.1700
Data Index: 5844918 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.6982. Min Act: -0.1700
Data Index: 8081159 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.5107. Min Act: -0.1700
Data Index: 2617365 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.5107. Min Act: -0.1700
Data Index: 5042797 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.3857. Min Act: -0.1700
Data Index: 3169446 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.3857. Min Act: -0.1700
Data Index: 6154514 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.4170. Min Act: -0.1700
Data Index: 4769873 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.3857. Min Act: -0.1700
Data Index: 4689884 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.3857. Min Act: -0.1700
Data Index: 5339949 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.3857. Min Act: -0.1700
Data Index: 658995 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.3232. Min Act: -0.1700
Data Index: 7402471 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.3232. Min Act: -0.1700
Data Index: 7546333 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.2920. Min Act: -0.1700
Data Index: 320221 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.2607. Min Act: -0.1700
Data Index: 2640925 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.2607. Min Act: -0.1700
Data Index: 7256858 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.2295. Min Act: -0.1700
Data Index: 4730073 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.2295. Min Act: -0.1700
Data Index: 2367437 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.2295. Min Act: -0.1700
Data Index: 6845415 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9170. Min Range: -7.9170
Max Act: 7.2607. Min Act: -0.1700
Data Index: 2888513 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19