Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1307. Min Range: -6.1307
Max Act: 6.1307. Min Act: -0.1700
Data Index: 7862926 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1307. Min Range: -6.1307
Max Act: 6.0370. Min Act: -0.1700
Data Index: 5637566 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1307. Min Range: -6.1307
Max Act: 6.0370. Min Act: -0.1700
Data Index: 5357542 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1307. Min Range: -6.1307
Max Act: 6.0057. Min Act: -0.1700
Data Index: 2134054 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.9432. Min Act: -0.1700
Data Index: 7759432 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.9120. Min Act: -0.1700
Data Index: 2313846 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.8495. Min Act: -0.1700
Data Index: 3359352 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.7245. Min Act: -0.1700
Data Index: 6574979 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.6932. Min Act: -0.1700
Data Index: 376679 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.7245. Min Act: -0.1700
Data Index: 7657109 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.6932. Min Act: -0.1700
Data Index: 6935713 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.6620. Min Act: -0.1700
Data Index: 1860449 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.6307. Min Act: -0.1700
Data Index: 5649076 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.6307. Min Act: -0.1700
Data Index: 7582284 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.5995. Min Act: -0.1700
Data Index: 814162 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.5682. Min Act: -0.1700
Data Index: 1263620 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.5682. Min Act: -0.1700
Data Index: 6854577 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.5370. Min Act: -0.1700
Data Index: 5716055 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.5370. Min Act: -0.1700
Data Index: 4052512 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1307. Min Range: -6.1307
Max Act: 5.5370. Min Act: -0.1700
Data Index: 6030625 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19