Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2168 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.8307. Min Act: -0.1700
Data Index: 3918372 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.7682. Min Act: -0.1700
Data Index: 3918368 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.7057. Min Act: -0.1700
Data Index: 6193017 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.6432. Min Act: -0.1700
Data Index: 792450 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.5495. Min Act: -0.1700
Data Index: 929560 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.4870. Min Act: -0.1700
Data Index: 1691710 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.4557. Min Act: -0.1700
Data Index: 606320 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.4557. Min Act: -0.1700
Data Index: 4402392 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.4245. Min Act: -0.1700
Data Index: 1598543 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.3620. Min Act: -0.1700
Data Index: 2760673 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.3620. Min Act: -0.1700
Data Index: 2870471 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.3307. Min Act: -0.1700
Data Index: 7400189 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.3307. Min Act: -0.1700
Data Index: 6748944 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.3307. Min Act: -0.1700
Data Index: 5206001 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.2995. Min Act: -0.1700
Data Index: 1878045 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.2995. Min Act: -0.1700
Data Index: 5147946 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.2682. Min Act: -0.1700
Data Index: 3990599 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.2682. Min Act: -0.1700
Data Index: 4244353 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.2682. Min Act: -0.1700
Data Index: 1101355 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8307. Min Range: -7.8307
Max Act: 7.2682. Min Act: -0.1700
Data Index: 5417410 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19