Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2481 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0911. Min Range: -7.0911
Max Act: 7.0911. Min Act: -0.1700
Data Index: 967919 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0911. Min Range: -7.0911
Max Act: 7.0286. Min Act: -0.1700
Data Index: 1628811 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.9036. Min Act: -0.1700
Data Index: 5474994 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.8098. Min Act: -0.1700
Data Index: 2997466 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.7786. Min Act: -0.1700
Data Index: 2071885 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.6848. Min Act: -0.1700
Data Index: 5522729 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.7161. Min Act: -0.1700
Data Index: 3740600 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.7161. Min Act: -0.1700
Data Index: 6867238 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.6848. Min Act: -0.1700
Data Index: 127787 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.6536. Min Act: -0.1700
Data Index: 2251761 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.6223. Min Act: -0.1700
Data Index: 4738725 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.6223. Min Act: -0.1700
Data Index: 505751 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.5598. Min Act: -0.1700
Data Index: 6573184 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.5598. Min Act: -0.1700
Data Index: 3078714 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.5598. Min Act: -0.1700
Data Index: 1546102 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.5286. Min Act: -0.1700
Data Index: 13525 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.5286. Min Act: -0.1700
Data Index: 6470755 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.4973. Min Act: -0.1700
Data Index: 4845420 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.4973. Min Act: -0.1700
Data Index: 2316329 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0911. Min Range: -7.0911
Max Act: 6.4661. Min Act: -0.1700
Data Index: 1500368 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19