Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3700 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.6279. Min Act: -0.1700
Data Index: 1058084 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.4404. Min Act: -0.1700
Data Index: 6519390 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.3466. Min Act: -0.1700
Data Index: 3286262 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.2529. Min Act: -0.1700
Data Index: 946360 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.2841. Min Act: -0.1700
Data Index: 6576343 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.2841. Min Act: -0.1700
Data Index: 4813748 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.2216. Min Act: -0.1700
Data Index: 816817 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.2216. Min Act: -0.1700
Data Index: 6519391 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.2216. Min Act: -0.1700
Data Index: 5469805 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.2216. Min Act: -0.1700
Data Index: 1946309 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.1904. Min Act: -0.1700
Data Index: 6516182 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.1591. Min Act: -0.1700
Data Index: 2077513 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.1591. Min Act: -0.1700
Data Index: 7067992 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.1904. Min Act: -0.1700
Data Index: 2073445 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.1279. Min Act: -0.1700
Data Index: 7438221 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.0966. Min Act: -0.1700
Data Index: 7806840 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.0966. Min Act: -0.1700
Data Index: 646960 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.0966. Min Act: -0.1700
Data Index: 7421183 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.1279. Min Act: -0.1700
Data Index: 3276536 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6279. Min Range: -6.6279
Max Act: 6.0966. Min Act: -0.1700
Data Index: 5142062 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19